JP3545624B2 - IMAGE RECOGNITION SYSTEM PERFORMANCE IMPROVING METHOD, DEVICE, AND RECORDING MEDIUM CONTAINING IMAGE RECOGNITION SYSTEM PERFORMANCE PROGRAM - Google Patents

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a method and apparatus for performing processing on a processing target, outputting the result, and improving the performance of a system having an adjustable recognition parameter group that determines the performance of the processing.
[0002]
[Prior art]
Examples of this type of system include a welding point recognition system for an arc light welding robot, a component inspection system for recognizing a defective product, an automatic surveillance camera system for recognizing a person, a fingerprint identification system, a voice print identification system, and a character recognition system. .
[0003]
This type of system includes two types, a system in which it is difficult to calculate the value of the recognition parameter group as an analytical solution, and a system in which the value of the recognition parameter group can be calculated as an analytical solution.
[0004]
When introducing and operating these two types of systems, it is essential to adjust the values of the recognition parameter group in order to improve the performance. Conventionally, for a system in which it is difficult to calculate the value of the recognition parameter group as an analytical solution that minimizes the performance evaluation function, the system administrator has manually adjusted the value of the recognition parameter group based on experience. Also, for a system that can calculate the value of a recognition parameter group as an analytical solution that minimizes the performance evaluation function, the value of the recognition parameter group is adjusted based on the analytical solution.
[0005]
[Problems to be solved by the invention]
However, the conventional method has the following two problems.
[0006]
1. Adjustment of a system in which it is difficult to calculate a value of a group of recognition parameters optimal for an operating environment as an analytical solution generally requires sufficient experience. Therefore, in the event of a malfunction that the system does not operate as expected by humans, it is necessary for a system administrator with sufficient experience to go to the site and collect and analyze vast amounts of information to adjust the values of the recognition parameter group. There are high human and time costs.
[0007]
2. In a system that performs a process on some input and outputs a result, and has a recognition parameter group that can be adjusted for the process, variables constituting a performance evaluation function are limited to state variables in the system. Therefore, the operation of the optimized system does not always follow the intention of the human.
[0008]
An object of the present invention is to provide a method and apparatus for improving the performance of an image recognition system and a recording medium on which a program for improving the performance of an image recognition system is recorded. Is to provide.
[0009]
Another object of the present invention is to provide an image recognition system performance improvement method and apparatus capable of adjusting the system so as to perform an operation in accordance with human intention, and a recording medium storing an image recognition system performance improvement program. .
[0010]
[Means for Solving the Problems]
According to a first aspect of the present invention, an image recognition system performance improvement method comprises:
A method for improving the performance of an image recognition system in which an image recognition system performance improvement apparatus performs a recognition process on an image to be recognized and outputs the result, and has an adjustable recognition parameter group that determines the performance of the recognition process And
An initial recognition parameter determining unit that determines an initial value of the recognition parameter group;
A step of inputting a correct answer to the recognition target image,
A communication unit for transmitting a recognition parameter group to the image recognition system;
A communication unit, when the image recognition system performs recognition processing on the recognition target image based on the recognition parameter group, as a result of the recognition processing, a maximum match between the recognition target image and the plurality of models; Receiving the processing time of the image recognition system;
A performance evaluation value calculation unit that calculates a performance evaluation value of the image recognition system for the recognition parameter group based on the correct answer, the result of the recognition processing, the maximum matching degree, and the processing time;
A determining unit for determining whether the performance evaluation value has reached a predetermined criterion;
When the performance evaluation value does not reach a predetermined criterion, a parameter improving unit changes the recognition parameter group so that the performance evaluation value is improved, and returns to the step of transmitting the recognition parameter group.
When the performance evaluation value reaches a predetermined criterion, an output unit outputs a recognition parameter group that realizes the performance evaluation value to the image recognition system.
Having.
[0011]
Therefore, the system can be adjusted to perform the operation according to human intention.
[0012]
According to a second aspect of the present invention, an image recognition system performance improvement method comprises:
A method for improving the performance of an image recognition system in which an image recognition system performance improvement apparatus performs a recognition process on an image to be recognized and outputs the result, and has an adjustable recognition parameter group that determines the performance of the recognition process And
An initial recognition parameter determining unit that determines an initial value of the recognition parameter group;
A step of inputting a correct answer to the recognition target image,
A communication unit for transmitting a recognition parameter group to the image recognition system;
A communication unit, when the image recognition system performs recognition processing on the recognition target image based on the recognition parameter group, as a result of the recognition processing, a maximum match between the recognition target image and the plurality of models; Receiving the processing time of the image recognition system;
A performance evaluation value calculation unit that calculates a performance evaluation value of the image recognition system for the recognition parameter group based on the correct answer, the result of the recognition processing, the maximum matching degree, and the processing time;
A determining unit that calculates a fitness in the genetic algorithm based on the performance evaluation value, and determines whether the fitness has reached a predetermined criterion;
When the fitness does not reach a predetermined criterion, a chromosome conversion unit converts the value of the recognition parameter group into a chromosome of a genetic algorithm,
The selecting unit, the step of selecting the chromosome based on the fitness,
Mating section, performing a mating operation on the selected chromosome to obtain an intermediate chromosome,
Mutant, a step of obtaining a new chromosome by performing a mutation operation on the intermediate chromosome,
A parameter conversion unit converts the new chromosome to a recognition parameter group, and returns to the step of transmitting the recognition parameter group.
When the fitness reaches a predetermined criterion, an output unit outputs a value of a recognition parameter group that realizes the fitness to the image recognition system.
Having.
[0013]
Therefore, it is possible to adjust the system so that the operation is performed according to human intention, and it is possible to significantly reduce the time cost and the human cost required for the adjustment.
[0014]
According to a third aspect of the present invention, an image recognition system performance improvement method comprises:
A method for improving the performance of an image recognition system in which an image recognition system performance improvement apparatus performs a recognition process on an image to be recognized and outputs the result, and has an adjustable recognition parameter group that determines the performance of the recognition process And
An initial recognition parameter determining unit that determines an initial value of the recognition parameter group;
A communication unit for transmitting a recognition parameter group to the image recognition system;
A communication unit, when the image recognition system performs recognition processing on the recognition target image based on the recognition parameter group, a maximum matching degree between the recognition target image and a plurality of models, and the image Receiving the processing time of the recognition system;
A performance evaluation value calculation unit that calculates a performance evaluation value of the image recognition system for the recognition parameter group based on the maximum matching degree and the processing time;
A determining unit that calculates a fitness in the genetic algorithm based on the performance evaluation value, and determines whether the fitness has reached a predetermined criterion;
When the fitness does not reach a predetermined criterion, a chromosome conversion unit converts the value of the recognition parameter group into a chromosome of a genetic algorithm,
The selecting unit, the step of selecting the chromosome based on the fitness,
Mating section, performing a mating operation on the selected chromosome to obtain an intermediate chromosome,
Mutant, a step of obtaining a new chromosome by performing a mutation operation on the intermediate chromosome,
A parameter conversion unit converts the chromosome into a recognition parameter group, and returns to the step of transmitting the recognition parameter group.
When the fitness reaches a predetermined criterion, an output unit outputs a value of a recognition parameter group that realizes the fitness to the image recognition system.
Having .
[0015]
Therefore, the time cost and human cost required for adjusting the system can be significantly reduced.
[0016]
BEST MODE FOR CARRYING OUT THE INVENTION
Next, embodiments of the present invention will be described with reference to the drawings.
[0017]
FIG. 1 shows an example in which the present invention is applied to a digit recognition system in which the value of a parameter group is difficult to calculate as an analytical solution. The correlation between the system performance improvement device, the digit recognition system, the operating conditions, and the processing target of the present invention is shown. Show. The relationship includes a format A (FIG. 1 (1)) and a format B (FIG. 1 (2)). The format A is a format in which the system performance improvement device 2 exists independently of the digit recognition system 1, and the format B Is a format in which the system performance improving device 2 is incorporated in the numeral recognition system 1. The following describes the format A, but the same applies to the format B.
[0018]
(First Embodiment)
The number recognition system 1 has a function of sensing the processing target 5 and recognizing the number. That is, the recognition processing device 4 in the numeral recognition system 1 calculates the degree of coincidence between the numeral models I1, I2,..., I9 and the processing target 5, and recognizes the numeral by obtaining a numeral model with a high degree of coincidence. The accuracy of recognition depends on the group of recognition parameters. The system performance improvement device 2 determines a recognition parameter group that derives the best performance by using the performance evaluation value of the system in consideration of the recognition result or the degree of coincidence, the correct answer for the processing target 5, the processing time, and the like. The operation condition 3 is a condition under which the numeral recognition system 1 operates, and includes a temperature, an illumination condition, and a correct answer for the processing target 5. The sensing result and the recognition result of the processing target 5 are affected by conditions such as temperature and lighting.
[0019]
FIG. 9 shows an example of the processing target 5 handled by the numeral recognition system 1. The processing targets A and B are affected by the operating condition 3 and are affected by noise, and the input images 6 to the digit recognition system 1 are as shown by a and b, respectively. The correct answer for the input image 6 is “9” for “a” and “0” for b.
[0020]
FIG. 2 shows a processing flow of the numeral recognition system 1.
[0021]
First, a noise-removed image is created by extracting pixels in which the sum of the difference between each pixel value of the input image 6 and the surrounding pixels S is smaller than the recognition parameter T (A) (step 11). Next, a binary image is created by extracting pixels having a pixel value G smaller than the recognition parameter (B) from the noise-removed image (step 12). Next, the degree of coincidence M (0) to M (9) between the created binary image and the numeral models I0 to I9 of the numerals 0 to 9 is calculated. Finally, the maximum matching degree Max = M (x) is obtained from the matching degrees M (0) to M (9), and if this is larger than the recognition parameter T (C), X is output as a recognition result. Further, the processing time T and the maximum coincidence Max are simultaneously output.
[0022]
If the input image 6 is a (FIG. 9), a noise-removed image a ′ is obtained in step 11, and a binary image a ″ is obtained in step 12.
[0023]
The degree of coincidence between the input image a and the numerical models I0 to I9 of the numerals 0 to 9 is represented by Ma (0) to Ma (9), respectively, and the input image b is represented by the numerical models I0 to I9 of the numerals 0 to 9 respectively. Are respectively Mb (0) to Mb (9), the necessary condition of the recognition parameter for achieving the correct recognition for the processing target 5 is Ma (9) with x being a variable of 0 to 9. )> T (C) and Ma (9) ≧ Ma (x) and Mb (0)> T (C) and Mb (0) ≧ Mb (x).
[0024]
If the recognition parameter group is not adjusted, the above-mentioned necessary condition may not be satisfied under a noisy condition, and for example, Ma (9) <T (C) or Mb (0) <Mb (8) may be satisfied. Would make a wrong recognition. Therefore, it is necessary to adjust the parameter group.
[0025]
FIG. 3 is a configuration diagram of a system performance improvement device 2 that adjusts a recognition parameter group to improve system performance, and FIG. 4 is a flowchart illustrating a flow of the process.
[0026]
The system performance improvement device 2 includes an initial recognition parameter determination unit 21, a correct answer input unit 22, a communication unit 23, a performance evaluation value calculation unit 24, a determination unit 25, an output unit 26, and a parameter improvement unit 27.
[0027]
The initial recognition parameter determination unit 21 determines an initial recognition parameter group T (A), T (B), T (C) (Step 31). The correct answer input unit 22 inputs the initial recognition parameter groups T (A), T (B), T (C) and the correct answer Y for the recognition target 5 and outputs them to the communication unit 23 (Step 32). The communication unit 23 transmits the recognition parameter groups T (A), T (B), and T (C) to the number recognition system 1 (Step 33). The digit recognition system 1 resets the recognition parameter group, performs recognition on the input image 6 under the operating condition 3, calculates the maximum coincidence Max, recognizes the recognition result X, the maximum coincidence Max, and the recognition processing time T. The communication unit 23 receives these and outputs them to the performance evaluation value calculation unit 24 together with the recognition parameter groups T (A), T (B), T (C), and the correct answer Y (step 34). The performance evaluation value calculation unit 24 calculates a performance evaluation value = Max / (| X−Y | + T) for the recognition parameter group, and together with the recognition parameter groups T (A), T (B), and T (C), determines the judgment unit 25. (Step 35). The determination unit 25 determines whether or not the performance evaluation value is equal to or greater than the threshold. If the performance evaluation value is equal to or greater than the threshold, the process proceeds to the output unit 27. If the performance evaluation value is less than the threshold, the process proceeds to the parameter improvement unit 27. T (C) is output (step 36). The parameter improving unit 26 sets the recognition parameter groups T (A), T (B), and T (C) to, for example, T (A) = Y (A) +0. 01, T (B) = T (B) +0.01, T (C) = T (C) +0.01, and outputs the result to the communication unit 23 (step 37). The output unit 27 outputs the recognition parameter groups T (A), T (B), and T (C) to the number recognition system 1 assuming that the recognition parameter group is set to a value adapted to the operating condition 3 (step 38). .
[0028]
In the above description, the processing for one parameter group is described as an example, but a plurality of parameter groups may be processed simultaneously. Further, the performance evaluation function may be (| XY- + T) / Max. In that case, the determination unit 25 determines whether the performance evaluation value is equal to or less than a certain threshold. Since the end condition of this processing is determined by determining the size of the performance evaluation value for the recognition target 5 with respect to the threshold value, it is not guaranteed that the performance evaluation value based on the output recognition parameter group is the maximum value or the minimum value. There is a possibility that the maximum value or the minimum value (local maximum value or local minimum value) within the range in which the recognition parameter is changed by the parameter improving unit 26. However, it is important that the performance evaluation value is large or small, and there is no practical problem.
[0029]
According to the present embodiment, in the case of FIG. 9, by adjusting the recognition parameter group using the correct answer Y and the recognition result for the processing target 5, the input image a is finally recognized as “9”, A recognition parameter group T (A), T (B), T (C) that recognizes "0" for the input image b is obtained.
[0030]
(Second embodiment)
Next, as a second embodiment of the present invention, an example will be described in which a genetic algorithm is used as a method for calculating and outputting a recognition parameter for minimizing or maximizing a performance evaluation value.
[0031]
FIG. 5 is a configuration diagram of a system performance improvement device according to the second embodiment of the present invention, and FIG. 6 is a flowchart showing the flow of the processing.
[0032]
The system performance improvement device 2 includes an initial recognition parameter determination unit 41, a correct answer input unit 42, a communication unit 43, a performance evaluation value calculation unit 44, a determination unit 45, a parameter improvement unit 46 using a genetic algorithm, and an output unit 47. . The parameter improving unit 46 includes a chromosome converting unit 46a, a selecting unit 46b, a mating unit 46c, a mutating unit 46d, and a parameter converting unit 46e.
[0033]
The initial recognition parameter determination unit 41 includes a plurality (m) of initial recognition parameter groups T ₁ (A), T ₁ (B), T 1 (C), T 2 (A), T 2 (B), T 2 (C),. .., Tm (A), Tm (B), Tm (C) are determined (step 61). The correct answer input unit 42 inputs the correct answer Y for the processing target 5 together with the initial recognition parameter group, outputs these to the communication unit 43, and further initializes the pointer j (step 62). The communication unit 43 transmits the j-th recognition parameter unit Tj (A), Tj (B), Tj (C) to the numeral recognition system 1 (Step 63). The numeral recognition system 1 resets the transmitted recognition parameter group, performs recognition on the processing target 5, calculates the maximum coincidence Max, and communicates the maximum coincidence Max, the recognition result X, and the processing time T. It is transmitted to the unit 43. The communication unit 43 receives the maximum coincidence Max, the recognition result X, and the processing time T, and outputs them to the performance evaluation value calculation unit 44 together with the recognition parameter group (step 64). The performance evaluation value calculation unit 44 calculates the performance evaluation value corresponding to the j-th recognition parameter group, for example, as Max / (| X−Y | + T) (step 65), and compares j with m (step 66). ), If j is smaller than m, j is incremented by 1 to output a recognition parameter group to the communication unit 43, a recognition parameter group is output to the communication unit 43, and the process returns to the communication unit 43. If j is equal to or greater than m, the determination unit 45 inputs the recognition parameter group from the performance evaluation value calculation unit 44 and calculates the fitness (for example, fitness = performance evaluation value) based on the m performance evaluation values. Then, it is determined whether or not the maximum fitness value among the m fitness values is equal to or greater than a certain threshold value (step 67). If the maximum performance evaluation value is less than the threshold value, the parameter improving unit 46 inputs the recognition parameter group, and the chromosome conversion unit 46a outputs the recognition parameter groups T1 (A) to T1 (C), T2 as shown in FIG. (A) to T2 (C),..., Tm (A) to Tm (C) are represented by binary numbers, and by connecting them, m chromosomes T1, T2,. (Step 68a). Then, as the selection unit 46b is shown in FIG. 8, performs a selection operation on each chromosome based on the m fitness, 2N (<m) pieces of chromosomes _{t 11,} t 12, · · ·, _tN1 , _tN2 ,..., _tN1 , _tN2 are selected (step 68b). Next, the mating operation on chromosome _t 11 _{~t N2} for mating portion 46c is selected to obtain an intermediate chromosome U1~U _m (step 68c). Next, the mutation section 46d performs a mutation operation on all chromosomes to obtain new chromosomes T1 'to T'm (step 68d). Next, the parameter conversion unit 46e converts each chromosome into each recognition parameter group in a procedure reverse to that of FIG. 7, that is, separates the joined chromosomes (in this example, decomposes them into three), and Is converted to a decimal number, the recognition parameter group is output to the communication unit 43, and the process returns to the communication unit 43 (step 72). If the largest one of the m performance evaluation values is equal to or greater than a certain threshold, the output unit 47 determines that the recognition parameter group for the performance evaluation value is set to a value adapted to the operation condition 3 and performs numeric recognition. Output to the system 1 (step 69).
[0034]
(Third embodiment)
However, the value of the recognition parameter group may be obtained without using the correct answer Y for the processing target 5. In that case, since the process of step 62 is not performed, the correct answer input unit 42 becomes unnecessary. In this case, Max / T can be considered as the performance evaluation function, and fitness = performance evaluation value can be considered as the fitness.
[0035]
Also in the present embodiment, the effects described in the first embodiment can be obtained in the same manner, and the time for obtaining the optimal parameters can be shortened.
[0036]
FIG. 10 is a block diagram in which the system performance improving device 2 described above is realized by a personal computer. This system performance improving device includes an input device 71, storage devices 72 and 73, an output device 74, a recording medium 75, and a data processing device 76. The input device 71 is for inputting the correct answer Y, the degree of coincidence Max, the recognition result X, and the processing time T from the number recognition system 1. The storage device 72 is for storing input data and intermediate calculation results. The storage device 73 is a hard disk. The output device 74 is for outputting a recognition parameter group and a recognition parameter group adapted to the operation condition to the numeral recognition system 1. The recording medium 75 is a recording medium such as an FD (floppy disk), CD-ROM, or MO (magneto-optical disk) on which a system performance improvement program including the processing shown in FIG. 4 or FIG. 6 is recorded. The data processing device 76 is a CPU that reads the system performance improvement program from the recording medium 75 into the storage device 73 and executes the program.
[0037]
【The invention's effect】
As described above, according to the present invention, when the system needs to be adjusted, such as when the system is introduced or when a system malfunction occurs, the recognition parameters are automatically set based on the conditions under which the system operates such as lighting conditions and temperature. By determining the group, significant reductions in human and time costs can be achieved. In addition, by automatically determining the recognition parameters based on the teaching data for the processing result, the system can be adjusted to perform an operation according to human intention. Furthermore, by automatically determining the recognition parameter group using a genetic algorithm based on the teaching data, the system is adjusted to perform the operation according to the human intention, and human and time costs are significantly reduced. Can be achieved.
[Brief description of the drawings]
FIG. 1 is a system configuration diagram of an embodiment of the present invention.
FIG. 2 is a diagram showing a processing flow of a recognition processing device 4;
FIG. 3 is a configuration diagram of a system performance improvement device 2.
FIG. 4 is a flowchart of a process according to the first embodiment of the present invention.
FIG. 5 is another configuration diagram of the system performance improvement device 2.
FIG. 6 is a flowchart of a process according to a second embodiment of the present invention.
FIG. 7 is an explanatory diagram of a method of converting a parameter group into a chromosome.
FIG. 8 is an explanatory diagram of an operation on a chromosome.
FIG. 9 is a diagram showing an example of a processing target handled by the numeral recognition system 1 in FIG. 1;
FIG. 10 is a block diagram showing another embodiment of the system performance improving device 2.
[Explanation of symbols]
REFERENCE SIGNS LIST 1 numeral recognition system 2 system performance improvement device 3 operating condition 4 recognition processing device 5 processing target 6 input image 11 to 12 step 21 initial recognition parameter determination unit 22 correct answer input unit 23 communication unit 24 performance evaluation value calculation unit 25 determination unit 26 parameter Improvement unit 27 Output units 31 to 38 Step 41 Initial recognition parameter determination unit 42 Correct answer input unit 43 Communication unit 44 Performance evaluation value calculation unit 45 Judgment unit 46 Parameter improvement unit 46a Chromosome conversion unit 46b Selection unit 46c Mating unit 46d Mutation unit 46e Parameter Conversion unit 47 Output units 61 to 69 Step 71 Input devices 72, 73 Storage device 74 Output device 75 Recording medium 76 Data processing device

Claims (9)

A method for improving the performance of an image recognition system in which an image recognition system performance improving apparatus performs a recognition process on an image to be recognized and outputs the result, and has an adjustable recognition parameter group that determines the performance of the recognition process And
An initial recognition parameter determining unit that determines an initial value of the recognition parameter group;
A step of inputting a correct answer to the recognition target image,
A communication unit for transmitting a recognition parameter group to the image recognition system;
A communication unit, when the image recognition system performs recognition processing on the recognition target image based on the recognition parameter group, as a result of the recognition processing, a maximum match between the recognition target image and the plurality of models; Receiving the processing time of the image recognition system;
A performance evaluation value calculation unit that calculates a performance evaluation value of the image recognition system for the recognition parameter group based on the correct answer, the result of the recognition processing, the maximum matching degree, and the processing time;
A determining unit for determining whether the performance evaluation value has reached a predetermined criterion;
When the performance evaluation value does not reach a predetermined criterion, a parameter improving unit changes the recognition parameter group so that the performance evaluation value is improved, and returns to the step of transmitting the recognition parameter group.
When the performance evaluation value reaches a predetermined criterion, an output unit outputs a recognition parameter group that realizes the performance evaluation value to the image recognition system.
A method for improving the performance of an image recognition system having: A method for improving the performance of an image recognition system in which an image recognition system performance improving apparatus performs a recognition process on an image to be recognized and outputs the result, and has an adjustable recognition parameter group that determines the performance of the recognition process And
An initial recognition parameter determining unit that determines an initial value of the recognition parameter group;
A step of inputting a correct answer to the recognition target image,
A communication unit for transmitting a recognition parameter group to the image recognition system;
A communication unit, when the image recognition system performs recognition processing on the recognition target image based on the recognition parameter group, as a result of the recognition processing, a maximum match between the recognition target image and the plurality of models; Receiving the processing time of the image recognition system;
A performance evaluation value calculation unit that calculates a performance evaluation value of the image recognition system for the recognition parameter group based on the correct answer, the result of the recognition processing, the maximum matching degree, and the processing time;
A determining unit that calculates a fitness in the genetic algorithm based on the performance evaluation value, and determines whether the fitness has reached a predetermined criterion;
When the fitness does not reach a predetermined criterion, a chromosome conversion unit converts the value of the recognition parameter group into a chromosome of a genetic algorithm,
The selecting unit, the step of selecting the chromosome based on the fitness,
Mating unit, performing a mating operation on the selected chromosome to obtain an intermediate chromosome,
Mutant, a step of obtaining a new chromosome by performing a mutation operation on the intermediate chromosome,
A parameter conversion unit converts the new chromosome into a recognition parameter group, and returns to the step of transmitting the recognition parameter group;
When the fitness reaches a predetermined criterion, an output unit outputs a value of a recognition parameter group that realizes the fitness to the image recognition system.
A method for improving the performance of an image recognition system having: A method for improving the performance of an image recognition system in which an image recognition system performance improvement apparatus performs a recognition process on an image to be recognized and outputs the result, and has an adjustable recognition parameter group that determines the performance of the recognition process And
An initial recognition parameter determining unit that determines an initial value of the recognition parameter group;
A communication unit for transmitting a recognition parameter group to the image recognition system;
A communication unit, when the image recognition system performs recognition processing on the recognition target image based on the recognition parameter group, a maximum matching degree between the recognition target image and a plurality of models, and the image Receiving the processing time of the recognition system;
A performance evaluation value calculation unit that calculates a performance evaluation value of the image recognition system for the recognition parameter group based on the maximum matching degree and the processing time;
A determining unit that calculates a fitness in the genetic algorithm based on the performance evaluation value, and determines whether the fitness has reached a predetermined criterion;
When the fitness does not reach a predetermined criterion, a chromosome conversion unit converts the value of the recognition parameter group into a chromosome of a genetic algorithm,
The selecting unit, the step of selecting the chromosome based on the fitness,
Mating section, performing a mating operation on the selected chromosome to obtain an intermediate chromosome,
Mutant, a step of obtaining a new chromosome by performing a mutation operation on the intermediate chromosome,
A parameter conversion unit converts the chromosome into a recognition parameter group, and returns to the step of transmitting the recognition parameter group.
When the fitness reaches a predetermined criterion, an output unit outputs a value of a recognition parameter group that realizes the fitness to the image recognition system.
A method for improving the performance of an image recognition system having: An image recognition system performance improvement device for performing a recognition process on a recognition target image and outputting a result thereof, and improving the performance of an image recognition system having an adjustable recognition parameter group that determines the performance of the recognition process. ,
An initial recognition parameter determination unit that determines an initial value of the recognition parameter group,
A correct answer input unit for inputting a correct answer for the recognition target image ,
It transmits the recognition parameter group to the image recognition system,
When the image recognition system performs a recognition process on the recognition target image based on the recognition parameter group, a result of the recognition process, a maximum matching degree between the recognition target image and a plurality of models, and A communication unit for receiving the processing time of the image recognition system ;
The correct answer , the result of the recognition process , the maximum degree of coincidence, and based on the processing time, a performance evaluation value calculation unit that calculates a performance evaluation value of the image recognition system for the recognition parameter group ,
A determining unit that determines whether the performance evaluation value has reached a predetermined criterion,
When said performance evaluation value does not reach the predetermined criterion, the recognition parameter group varied as said performance evaluation value is improved, and the parameter correction part for outputting to the communication unit,
When said performance evaluation value has reached a predetermined standard, the image recognition system performance improvement device having <br/> an output unit for outputting a recognition parameter group for realizing the performance evaluation value on the image recognition system. An image recognition system performance improvement device for performing a recognition process on a recognition target image and outputting a result thereof, and improving the performance of an image recognition system having an adjustable recognition parameter group that determines the performance of the recognition process. ,
An initial recognition parameter determination unit that determines an initial value of the recognition parameter group,
A correct answer input unit for inputting a correct answer for the recognition target image ,
It transmits the recognition parameter group to the image recognition system,
When the image recognition system performs a recognition process on the recognition target image based on the recognition parameter group, a result of the recognition process, a maximum matching degree between the recognition target image and a plurality of models, and A communication unit for receiving the processing time of the image recognition system ;
Said correct answer, the recognition result of the process, the maximum degree of coincidence, and based on said processing time, the calculating the performance evaluation value of the image recognition system for recognizing parameter group performance evaluation value calculations unit,
Calculating a fitness in the genetic algorithm based on the performance evaluation value, a determination unit to determine whether the fitness has reached a predetermined criterion,
If the fitness has not reached a predetermined reference, and chromosomal converter for converting the value of the recognition parameter group into the chromosome of the genetic algorithm,
A selection unit that selects the chromosome based on the fitness,
A mating unit that performs a mating operation on the selected chromosome to obtain an intermediate chromosome,
A mutated portion that performs a mutation operation on the intermediate chromosome to obtain a new chromosome,
A parameter conversion unit that converts the new chromosome into a recognition parameter group and outputs the data to the communication unit ,
If the fitness has reached a predetermined standard, the image recognition system performance improvement device having <br/> an output section for outputting a value of the recognition parameter group to realize the adaptability to the image recognition system. An image recognition system performance improvement device for performing a recognition process on a recognition target image and outputting a result thereof, and improving the performance of an image recognition system having an adjustable recognition parameter group that determines the performance of the recognition process. ,
An initial recognition parameter determination unit that determines an initial value of the recognition parameter group,
It transmits the recognition parameter group to the image recognition system,
When the image recognition system performs recognition processing on the recognition target image based on the recognition parameter group, a maximum matching degree between the recognition target image and a plurality of models, and processing of the image recognition system. A communication unit for receiving time ;
A performance evaluation value calculation unit that calculates a performance evaluation value of the image recognition system for the recognition parameter group based on the maximum matching degree and the processing time ,
Calculating a fitness in the genetic algorithm based on the performance evaluation value, a determination unit to determine whether the fitness has reached a predetermined criterion,
If the fitness has not reached a predetermined reference, and chromosomal converter for converting the value of the recognition parameter group into the chromosome of the genetic algorithm,
A selection unit that selects the chromosome based on the fitness,
A mating unit that performs a mating operation on the selected chromosome to obtain an intermediate chromosome,
A mutated portion that performs a mutation operation on the intermediate chromosome to obtain a new chromosome,
A parameter conversion unit that converts the new chromosome into a recognition parameter group and outputs the data to the communication unit ,
If the fitness has reached a predetermined standard, the image recognition system performance improvement device having <br/> an output section for outputting a value of the recognition parameter group to realize the adaptability to the image recognition system. An image recognition system performance improvement program for performing the recognition process on the recognition target image and outputting the result, and improving the performance of the image recognition system having an adjustable recognition parameter group that determines the performance of the recognition process is recorded. A recording medium,
A process of determining an initial value of the recognition parameter group;
A process of inputting a correct answer to the recognition target image ;
A process of transmitting the recognized parameter group to the image recognition system,
When the image recognition system performs a recognition process on the recognition target image based on the recognition parameter group, a result of the recognition process, a maximum matching degree between the recognition target image and a plurality of models, and a process of receiving the processing time of the image recognition system,
A process of calculating a performance evaluation value of the image recognition system for the recognition parameter group based on the correct answer , the result of the recognition process , the maximum degree of coincidence, and the processing time ;
Processing for determining whether the performance evaluation value has reached a predetermined criterion,
When said performance evaluation value does not reach a predetermined reference, and the said recognition parameter group varied as performance evaluation value is improved, the flow returns to the process of transmitting the recognition parameter group processing,
When said performance evaluation value has reached a predetermined standard, were recorded image recognition system upgrade program for executing a process of outputting a recognition parameter group for realizing the performance evaluation value on the image recognition system to the computer recoding media. An image recognition system performance improvement program for performing the recognition process on the recognition target image and outputting the result, and improving the performance of the image recognition system having an adjustable recognition parameter group that determines the performance of the recognition process is recorded. A recording medium,
A process of determining an initial value of the recognition parameter group;
A process of inputting a correct answer to the recognition target image ;
A process of transmitting the recognized parameter group to the image recognition system,
When the image recognition system performs a recognition process on the recognition target image based on the recognition parameter group, a result of the recognition process, a maximum matching degree between the recognition target image and a plurality of models, and a process of receiving the processing time of the image recognition system,
A process of calculating a performance evaluation value of the image recognition system for the recognition parameter group based on the correct answer , the result of the recognition process , the maximum degree of coincidence, and the processing time ;
Calculating the fitness in the genetic algorithm based on the performance evaluation value, processing to determine whether the fitness has reached a predetermined criterion,
If the fitness has not reached the predetermined reference, the process of converting the value of the recognition parameter group into the chromosome of the genetic algorithm,
Processing to select the chromosome based on the fitness,
A process of performing a mating operation on the selected chromosome to obtain an intermediate chromosome,
A process for obtaining a new chromosome by performing a mutation operation on the intermediate chromosome,
A process of converting the new chromosome into a recognition parameter group and returning to a process of transmitting the recognition parameter group,
If the fitness has reached a predetermined standard, the image recognition system performance improvement for executing <br/> and processing of outputting the value of the recognition parameter group to realize the adaptability to the image recognition system to the computer A recording medium on which a program is recorded. An image recognition system performance improvement program for performing the recognition process on the recognition target image and outputting the result, and improving the performance of the image recognition system having an adjustable recognition parameter group that determines the performance of the recognition process is recorded. A recording medium,
A process of determining an initial value of the recognition parameter group;
A process of transmitting the recognized parameter group to the image recognition system,
When the image recognition system performs recognition processing on the recognition target image based on the recognition parameter group, a maximum matching degree between the recognition target image and a plurality of models, and processing of the image recognition system. Processing to receive time ;
A process of calculating a performance evaluation value of the image recognition system for the recognition parameter group based on the maximum matching degree and the processing time ;
Calculating the fitness in the genetic algorithm based on the performance evaluation value, processing to determine whether the fitness has reached a predetermined criterion,
If the fitness has not reached the predetermined reference, the process of converting the value of the recognition parameter group into the chromosome of the genetic algorithm,
Processing to select the chromosome based on the fitness,
A process of performing a mating operation on the selected chromosome to obtain an intermediate chromosome,
A process for obtaining a new chromosome by performing a mutation operation on the intermediate chromosome,
A process of converting the chromosome into a recognition parameter group and returning to a process of transmitting the recognition parameter group,
If the fitness has reached a predetermined standard, the image recognition system performance improvement for executing <br/> and processing of outputting the value of the recognition parameter group to realize the adaptability to the image recognition system to the computer A recording medium on which a program is recorded.

Images