JP3014155B2 - Optical pattern recognition and classification method - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an optical pattern recognition and classification method used in the field of optical information processing.
That is, the present invention relates to a recognition associating process and a classification process, and more particularly, to an optical pattern recognition and classification method by arithmetic processing of information processing in the optical measurement field and image processing field.

[0002]

2. Description of the Related Art Conventionally, there are a matched filter method and a joint transform method as optically performing a correlation operation. The former method uses a two-dimensional reference pattern.
After the Fourier transform of the antenna, a reference wave is irradiated,
Create a Rier transform hologram and use it as a filter.
By superimposing the Fourier transform image of the test pattern,
A correlation operation is performed. In the latter method, a joint Fourier transform image of a test pattern and a reference pattern is recorded as an intensity pattern, and this is irradiated with a plane wave to perform a correlation operation. .

[0003] However, in both methods, the reference pattern group is prepared by the number of patterns to be identified and classified.
For the presentation of the test pattern, there is a method in which the pattern with the maximum correlation output, that is, the result obtained based on the autocorrelation output is used as the detection result, so that the number of reference patterns is increased. In addition, the reference pattern to be stored is increased, the load on the two-dimensional or three-dimensional spatial light modulator is increased, and the ability as a discriminating / classifying device is governed by the ability of the spatial light modulator. And could not be used as a substantially better optical identification associative device.

In addition, the present inventors have introduced a feedback system for changing the amount of light applied to the reference pattern based on the correlation obtained by the latter method, so that the number of reference patterns can be reduced. It has been clarified that the increase and the efficiency of discrimination and association of the test pattern can be improved, but it is desired to further increase the number of test patterns that can be substantially recognized and classified. Although many recognition and classification methods using neural networks have been proposed, if it is necessary to add a new pattern to be recognized and classified after learning, the weight of the connection is re-learned and created. It was not rational because it took a lot of time to learn.

[0005]

SUMMARY OF THE INVENTION The present invention has been made in order to solve the above-mentioned problems, and the number of reference patterns to be recorded is very small, and many test patterns can be identified. An object of the present invention is to provide an optical pattern recognition and classification method that can be classified.

[0006]

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned technical problems, and an optical pattern is provided.
In the recognition and classification method, a correlation output between a test pattern belonging to a class to be classified and classified and a plurality of reference patterns is taken a plurality of times, and a parameter indicating a representative value and a variation of a set of obtained correlations is obtained. -Members corresponding to the plurality of reference patterns for each class to be recognized and classified on the basis of data
After each of the ship functions is created, a member of each correlation output between the test pattern and the plurality of reference patterns and each of the membership functions assigned to each of the classes to be recognized and classified. Taking each of the ship values and the smallest of the obtained member-ship values; or
The optical pattern recognition / classification method is characterized in that the average value of the membership values belongs to the class to be recognized / classified of the test pattern.

The correlation output between the plurality of reference patterns takes the peak value of the auto-correlation output or the cross-correlation output of the test pattern and the plurality of reference patterns. It is suitable. The correlation output between the plurality of reference patterns and the total light amount in the light receiving range corresponding to the spread of the autocorrelation output or the cross-correlation output between the test pattern and the plurality of reference patterns are obtained. It is preferable to set the average light amount. The correlation output between the plurality of reference patterns is a peak value of the autocorrelation output or the cross-correlation output of the test pattern and the plurality of reference patterns. It is preferable to set the total light amount or the average light amount in the light receiving range according to the spread of the correlation output.

Preferably, each correlation output with a plurality of reference patterns is obtained using a matched filter. Further, each correlation output with a plurality of reference patterns is obtained by calculating each intensity pattern obtained by individually performing joint Fourier transform of the test pattern and each reference pattern. ,again,
Each intensity pattern obtained by optically individually performing a Fourier transform, or performing a joint Fourier transform of the test pattern and each reference pattern collectively. It is preferable to obtain the optical signals by optically collectively Fourier-transforming them again. Each correlation output with a plurality of reference patterns is obtained by superimposing each reference pattern on a test pattern represented by a light transmittance distribution or a light reflectance distribution and incoherent light. It is preferable that the light amount is reflected and transmitted.

[0009]

According to the above-mentioned optical pattern recognition / classification method, patterns belonging to classes to be recognized / classified are selected.
By taking the degree of correlation between the pattern and the reference pattern, the degree of correlation that shares the features included in each reference pattern is equal to the number of reference patterns for each pattern to be recognized and classified. The obtained set of correlation degrees is expressed as a membership function taking into account the temporal instability of the spatial light modulator and the fluctuation amount of the correlation degree due to spec noise.

Next, when identifying and classifying the pattern to be inspected, the member pattern is determined based on the degree of correlation with each reference pattern.
By matching with the ship function, the degree of coincidence with the class to be recognized and classified can be obtained by the minimum value or the average value of the membership values.

Next, the optical correlation processing method of the present invention will be specifically described with reference to examples, but the present invention is not limited thereto.

[0012]

FIG. 1 is a schematic block diagram showing the function of an optical correlation processing apparatus according to an example of the optical correlation processing method of the present invention.

In the optical arrangement diagram of FIG. 1, the optical correlation processing device includes an image output means 1, an optical Fourier transform means 2, an image output means 3, an optical Fourier transform means 4, a light detection means. 5 is a known congruent Fourier transform optical system essentially consisting of

One pattern to be recognized and classified and a reference pattern group drawn on the image display device 16 are read out by the coherent light beam 12 emitted from the laser 11, and the screen is scanned by the Fourier transform lens 21. A joint Fourier transform pattern is formed on the pattern 31. This joint Fourier transform pattern is read by a two-dimensional photoelectric conversion element 32, drawn on an electric address type liquid crystal light valve (hereinafter abbreviated as LCLV) 35 by a liquid crystal drive circuit 33, and read by a light beam 37. The Fourier transform is again performed by the Fourier transform lens 41, and the correlation intensity on the screen 42 is detected by the two-dimensional photoelectric conversion element 43.

In the method according to the present invention, the degree of correlation between the pattern to be recognized and classified and each reference pattern is detected by the above-mentioned optical system, and then the computer 51 recognizes each of the patterns to be recognized. Based on the degree of correlation with each reference pattern, a membership function corresponding to the reference pattern is created by the method described below, and the recognition classification of the unknown pattern is compared with the membership function. It is characterized by performing by comparison.

Here, an example of a method for creating the membership function will be described below. For example, two character patterns E and V are selected as a reference pattern group, and a character pattern to be recognized and classified is set to H, and as shown in FIG. It is assumed that a character pattern to be recognized and classified is drawn on the image display device 16 at the interval at the center of the concentric circle. In this case, the output of the two-dimensional photoelectric conversion element 43, that is, the correlation output between the character pattern H and each reference character pattern appears at each corresponding reference character position drawn on the pattern display device. , As shown in FIG.

Here, a larger correlation value is represented by a larger circle. This is because the two parallel lines and horizontal bars constituting H react with the horizontal bars and vertical bars of the components of each reference character pattern, resulting in a difference in the correlation output intensity as illustrated. is there. In FIG. 3, the autocorrelation appearing on the optical axis is omitted here because it has no relation here.

The correlation output intensity obtained in this manner is sent to the computer 51 and stored in the memory 51. Similarly, patterns to be identified and classified are successively presented on the image display device 16 and obtained. The peak value of the correlation strength is further stored in the computer 51 one after another. Further, these operations are performed a plurality of times for each pattern to be identified and classified. This is because the peak value of the correlation output intensity is affected by the influence of spec noise due to coherent light, the temporal instability of the image display device 16 and the LCLV 35, and the input timing of the signal of the two-dimensional photoelectric conversion element 32. This is because if the recognition and classification are performed using only one correlation output value, accurate identification and classification cannot be performed. Therefore, the average value and the standard deviation of the peak values for the patterns belonging to each class are calculated from a plurality of data, and the members of the peak values of the correlation output intensity for the E and V patterns are calculated. The ship function is trapezoidal, for example, three times the standard deviation from the average is a membership value of 1, and three times the standard deviation is a membership value of 0, corresponding to the hypotenuse of the trapezoid. The size of the part to be performed is set to be equal to three times the standard deviation.

FIG. 4 is a graph showing the peak value of the correlation output with respect to E and V when the pattern to be identified and classified as described above is H, as a membership function. In this way, the membership functions are created for all the classes to be recognized and classified, and the computer 5
1 is stored together with information on the class to be recognized and classified. However, since the standard deviation amount happens to be extremely small in a plurality of trials, it is necessary to add a slight correction.

Next, in FIG. 2, an unknown character pattern is presented in place of the character pattern H, and the peak value of the correlation output intensity for each reference pattern is calculated by the method described above. , And is compared with the membership function of the pattern to be recognized and classified. For example, suppose that the membership functions for the patterns H, W, and N to be recognized and classified are those shown in FIGS. 4, 5, and 6, respectively. At this time, it is assumed that the peak value of the correlation output intensity of the unknown character pattern is output at point a for pattern E and output at point b for pattern V. FIG. 7 is a graph showing the membership values of the points a and b with respect to the pattern to be recognized and classified. In the above case, only values of 1, 0 were shown,
There may be a value in a portion corresponding to the oblique side of the trapezoid, and generally, the membership value is an analog value.

Now, from the membership values shown in FIG.
If a fuzzy logical AND operation is performed, the minimum value of the membership value of the pattern to be recognized and classified will be obtained. For unknown patterns, patterns H, W, N
Are 1, 0, 0, respectively. Therefore, the unknown pattern can be said to be 100% pattern H. On the other hand, if there are a number of patterns in which the minimum value of the membership value is not 0, the degree of a certain pattern can be estimated by using the values of the minimum values.

Further, the arithmetic mean of the membership values shown in FIG. 7 can be used as a judgment material. That is, in this case, for unknown patterns, the patterns H, W, and H are:
Since they are 1, 0.5 and 0, respectively, the degree of each pattern can be estimated. However, in the case of using arithmetic mean, an answer may be obtained even if the degree of correlation with a certain reference pattern does not match at all. It is meaningful as an auxiliary operation when it is difficult to obtain an answer by the operation. That is, for some reason, there is a significant deviation from the state when the average value is taken, and only one reference pattern and the member
If the ship value is 0 and the other reference pattern is 1, the AND operation cannot provide a correct answer. In this case, it is possible to use an arithmetic mean as a second candidate.

In the above-described embodiment, the membership function is trapezoidal. However, the membership function is not limited so long as it is a so-called convex fuzzy set. Even if there is, it does not matter. Incidentally, the correlation output intensity can be obtained in the same manner by taking the total light amount in the light receiving range according to the spread of the correlation output or the average light amount in addition to the peak value. In general, the correlation output is obtained when two patterns are A (x, y) and B (x, y).
It is represented by the following equation. I (x ′, y ′) = A (x, y) B ^* (x′−x,
y'-y) dxdy Here, ^* indicates a complex conjugate amount.

From this equation, it can be seen that the correlation output has twice the size of the pattern. Therefore,
From the peak value, the total light amount in the area in consideration of the spread or the average light amount can be obtained. FIG. 8 schematically shows the distribution of the correlation light amount, but the degree of overlap of the two patterns is expressed by being shifted vertically in the plane of the paper. In this case, for example, pattern E and pattern E
As shown in FIG. 8A, the correlation light quantity of the pattern H becomes a peak value when they completely overlap each other, and when the pattern H is displaced by the size of the pattern as shown in FIG. Since one of the vertical bars overlaps with the vertical bar of the pattern E, the correlation light amount can be detected although it is smaller than the peak value.

FIG. 8C shows the distribution of the correlation light quantity between the pattern E and the pattern H created in this manner. A large circle at the center indicates the peak light quantity, and a small upper and lower circle. The circles indicate the response of the horizontal bar, and the small horizontal circles indicate the response of the vertical bar. Therefore, in the total light amount or the average light amount, the characteristic of each pattern not found in the peak light amount is as follows.
Information that is better reflected can be obtained.

FIG. 9 shows a reference pattern E created based on the average light quantity in the light receiving range corresponding to the spread of the correlation output obtained when an experiment was actually performed using the above-described joint Fourier transform. The membership function of the pattern to be identified and classified with respect to V (15 patterns in the alphabet) is shown. The solid line is a membership function for pattern E, and the dashed line is
The abscissa indicates the membership function for the pattern V, and the abscissa indicates the average light amount of the correlation output. However, 1
Some of them have only one membership function, but this is omitted because one membership function did not fit in the scale of the horizontal axis.

FIG. 10 shows the results obtained by experiments using the joint Fourier transform. The unknown patterns are represented by alphabetical 15 patterns, each representing the degree of identification and classification of each pattern derived from the fuzzy logical AND operation result obtained when presented three times. It is. The alphabet on the left side is the input pattern, and the numerical values in the first and second parentheses indicate the average light amount of the correlation measured for the reference patterns E and V, respectively.
The alphabet on the right side is a recognition character obtained by performing a fuzzy-logical AND operation on the membership values in FIG. 9, and the numerical value is obtained by multiplying the AND operation result by 100.

Although there are several such confusing ones, if the highest one is selected, all the patterns are identified by only two reference patterns. This is not seen in conventional correlation processing using general autocorrelation. It can be seen from FIG. 10 that the set of patterns T, L, and I and the set of patterns K and M are particularly confusing, because the characteristics of each pattern are similar. Yes, even as it is, it can be used to perform recognition or classification by taking one having a high degree of correlation. However, even when this effect is completely removed and the system is used for an application for performing complete recognition, it can be realized by a very simple process. That is, the confusing membership function between patterns can be realized by incorporating one non-overlapping pattern. This is because if any one of the membership values is 0, a fuzzy logical AND operation is performed.
This is because it recognizes a different pattern.

Further, even if the number of classes and patterns to be identified and classified increases, it is possible to easily cope with them. This is because it is only necessary to create a membership function for the increased pattern. In this case, there is no need for an operation such as changing all the weights of all the connections connecting the neurons by additional learning, as in a normal neural network. In the neural network, when the number of classes and patterns to be identified and classified increases,
There is a problem that the learning time becomes very long due to an increase in the number of neurons, but such a problem does not occur in the pattern identification and classification method of the present invention.

Further, when used for applications such as association,
By associating the original pattern from the defect pattern by extending the degree of expansion of the membership function to a value larger than that in consideration of the fluctuation of the optical system, particularly, to the side having a lower correlation strength. Can be. Conversely, when associating a main pattern with a pattern to which extra information is added, the degree of spread of the membership function is extended to the side with a higher correlation strength, thereby obtaining the original pattern. Can be associated with.

Further, it can be used for purposes such as determining whether or not there is a defect. In this case, it is the reverse of the case of association, and the member created in consideration of the fluctuation of the optical system.
If the spread of the ship function is exceeded, for example, if it exceeds three times the standard deviation due to the fluctuation of the optical system, it is possible to use such a method as to consider that there is a defect.

In the above embodiment, the reference pattern 2
Thus, at least 15 patterns could be identified, but very roughly considering the capabilities of the method of the present invention, for example, the dynamic range of the detected correlation output is 1: 100. Assuming that the range in which the membership value of one membership function is not 0 has a spread of 10, 1 for N reference patterns
This means that an orthogonal area of 0 ^N is created. Since it is sufficient to include the pattern to be identified and classified in this, a very small number of reference patterns and a very large number of different patterns are used.
Can be identified as grain boundaries. Furthermore, fuzzy AN
Since the D operation is used, it is not necessary to assign a membership function to a completely orthogonal region when a decision is made to allow ambiguity, and the number of patterns that can be identified is:
It can expand further.

Both the peak value of the correlation output and the average light amount of the light receiving area according to the spread of the correlation pattern are used as members.
When used as a ship function, information having two different properties can be obtained for one reference pattern. Therefore, the number of reference patterns can be further reduced,
Reliable recognition classification can be performed from a lot of information.

In this embodiment, a joint Fourier transformer is used as an optical system for obtaining a correlation output. In this case, however, it is advantageous in that it is easy to add or rewrite a reference pattern. There is. Furthermore, in order to improve the classification and classification ability,
It is better not to be a joint Fourier transform correlator. The reason for this is
If the reference pattern group and the test pattern are Fourier-transformed at the same time, the contrast ratio of the multiple interference fringe patterns on the screen 31 in FIG. 1 decreases as the number of reference patterns increases. In addition, when the obtained correlation output is reduced, the dynamic range to which the membership function is assigned is reduced, and the pattern discriminating ability is reduced substantially. Therefore, the correlation processing method for avoiding the decrease in the correlation output is more efficient. Next, an embodiment using such a correlation processing method will be described.

[0035]

Embodiment 2 FIG. 11 shows an optical system for reproducing a known matched filter. As the matched filter 61, a pattern obtained by optically Fourier-transforming a plurality of reference patterns in advance and performing multiplex recording while changing the irradiation direction of the plane wave for each reference pattern is used. As shown in FIG. 11, a light beam 12 emitted from a laser 11 is expanded to an appropriate light beam diameter by a beam expander 13, and irradiates a pattern to be identified and classified drawn on an image display device. . Next, the light beam having the complex amplitude distribution of the pattern is Fourier-transformed by the Fourier transform lens 21, and irradiates the multiple interference fringe pattern drawn on the matched filter. At this time,
From a reference pattern having the same spatial frequency spectrum as the pattern to be identified and classified, diffracted light is emitted in the direction of the plane wave used when the reference pattern was created.

When this diffracted light is condensed on the screen 31 by the condensing lens 22, one of the diffracted lights becomes a reference pattern.
The pattern is a cross-correlation pattern between the pattern to be identified and classified, and the other is a convolution. Since the position where the cross-correlation output by each reference pattern appears is known in advance, the peak value of the correlation output intensity at that position or the total amount of light can be measured. Hereinafter, the process of measuring the correlation output intensity for the other patterns to be identified and classified and creating the membership function is the same as in the first embodiment, and a description thereof will be omitted.

In this case, since the Fourier component of each reference pattern is not superimposed on the matched filter,
The degree to which the contrast ratio of the correlation output decreases as the reference pattern increases is reduced. Therefore, since the dynamic range to which the membership function is assigned is hardly reduced, an extremely large number of patterns can be identified with a small number of reference patterns.

The same effect can be obtained by using another type of joint Fourier transform device. For example, the joint Fourier transform of each reference pattern of the joint Fourier transform and the pattern to be recognized and classified is performed individually and simultaneously in parallel using a lens array. This eliminates the problem that the Fourier transform components of the respective reference patterns overlap each other and lower the contrast ratio of the cross-correlation strength between the reference pattern and the pattern to be recognized and classified. Further, unlike the matched filter, the reference pattern can be increased or rewritten, so that more flexible processing can be performed. For example, in recognition, when the reference pattern set in advance cannot completely separate the images,
This can respond to a request to rewrite a part of the reference pattern.

Since the first and second embodiments are based on the coherent optical diameter, they have a feature that they are resistant to the translational deviation of the input pattern. This is because the correlation output position moves in response to the translation shift of the input pattern.

Next, an example of an optical system that is simple and relatively easy to integrate will be described.

Embodiment 3 An example shown in FIG. 12 is a known incoherent correlation optical system. As the optical system, as the optical system, the image display device 16 and the reference pattern mask 62 are arranged close to each other, and the output of the product of the pattern drawn on the image display device 16 and the reference pattern is output. The condensing lens array 71 converges the light on the screen 31 and detects the output from each reference pattern condensed by the two-dimensional photoelectric conversion element 43. On the image display device 16, patterns to be identified and classified are arranged and displayed in an array for pixels corresponding to the reference pattern mask 62.

In this case, a cross-correlation peak between each reference pattern and the pattern to be identified and classified is detected. In the following operation, other patterns to be identified and classified are sequentially displayed on the image display device, and based on these output values,
By creating membership functions for each of the patterns to be identified and classified, the same number as in the first and second embodiments can be obtained. However, there is no tolerance for the translational deviation of the input pattern,
It has a very simple configuration and has the property of being easily integrated.

The optical correlation processing system used in the above embodiment may be of any type. Various optical systems have also been proposed for the joint Fourier transform correlation optical system, but the screen 31 and the two-dimensional photoelectric conversion element 3 shown in FIG.
2. The same can be achieved by using an optically-addressed liquid crystal light valve instead of the pattern processing device 33 and the electrically-addressed liquid crystal light valve 35.

In the present invention, the part functioning as a spatial light modulator has a difference in specifications, but in principle, all of them are of the same electrical address type and optical address type. Can be used. Further, an analog type or a digital type can be used. Most of the devices described below belong to analog devices, but devices using ferroelectric materials correspond to digital devices. Examples of the electric address type include PLZT and KD in addition to the liquid crystal light valve described above.
Those to which an electro-optical effect is added, such as P and BSO, are often used.

In the example of the optical address type, a material in which a photoconductive layer is combined with the same material as the electric address type is generally used. However, in a crystal having a photovoltaic effect such as BSO or BaTiO _3, a photo-induced refractive index change occurs due to spontaneous polarization according to the input light intensity, so that it is not necessary to add a photoconductive layer. Note that these spatial light modulators can be configured as a transmission type or a reflection type.

However, in the case of an optical address type in which the read light completely cancels the information of the write light, the wavelength range of the read light and the write light is separated so that the read light affects the write information. It is necessary to devise such measures as not to give When an electric address type is used, a two-dimensional photoelectric conversion element for obtaining the input information and a driving circuit therefor are required, but there is an advantage that the signal is easily processed.

[0046]

As described above, the above-described effects are obtained by the optical pattern recognition / classification method of the present invention. Summarizing them has the following remarkable technical effects. First, by presenting a small number of reference patterns, an optical pattern recognition method capable of recognizing and classifying a very large number of patterns could be provided.

Second, by including time-series fluctuations of the spatial light modulator and time-series fluctuations such as speckle noise in the membership function of the degree of correlation created based on statistical quantities. Thus, an optical pattern recognition / classification method capable of eliminating the uncertainty of judgment in analog processing can be provided.

Third, by performing a fuzzy-logical AND operation of the membership function of the correlation degree of each reference pattern of the pattern to be recognized and classified, an optical system capable of performing highly accurate recognition and classification. And a method for recognizing and classifying patterns. Fourth, even when a new pattern to be recognized and classified is added, it can be easily executed by creating a membership function of the degree of correlation of each reference pattern with respect to this pattern. An optical pattern recognition classification method can be provided.

Fifth, even if the recognition result is confusing,
To provide an optical pattern recognition / classification method that can be easily and completely recognized by adding a small number of reference patterns and newly creating a membership function for this pattern. Was completed. Sixth, recognition, classification,
By adjusting the degree of expansion of the membership function separately from the fluctuation of the optical system according to the application such as association, an optical pattern recognition method capable of performing flexible processing could be provided. .

[Brief description of the drawings]

FIG. 1 is a schematic configuration diagram showing a joint Fourier transform optical system as an example used as an optical correlation processing device in the optical pattern recognition / classification method of the present invention.

FIG. 2 shows a pattern to be recognized and classified and a reference pattern group when a joint Fourier transform optical system is used as an optical correlation processing device in the optical pattern recognition and classification method of the present invention. It is a figure which shows a mode that displayed.

FIG. 3 is a diagram showing a state of a correlation output when a joint Fourier transform optical system is used as an optical correlation processing device in the optical pattern recognition / classification method of the present invention.

FIG. 4 is a diagram showing a membership function created based on the degree of correlation of each reference pattern with respect to one pattern to be recognized and classified in the optical pattern recognition and classification method of the present invention. is there.

FIG. 5 is a diagram showing a reference pattern for another pattern to be recognized and classified in the optical pattern recognition / classification method of the present invention;
FIG. 6 is a diagram illustrating a membership function created based on the degree of correlation between the members.

FIG. 6 shows a membership function created based on the degree of correlation of each reference pattern with respect to another pattern to be recognized and classified in the optical pattern recognition and classification method of the present invention. FIG.

FIG. 7 is a table showing membership values of a correlation measured for an unknown pattern with respect to a pattern to be recognized and classified in the optical pattern recognition and classification method of the present invention. FIG.

FIG. 8 is a diagram schematically showing a cross-correlation pattern used in the optical pattern recognition / classification method of the present invention.

FIG. 9 is a diagram showing membership values of 15 patterns to be recognized and classified for two reference patterns experimentally obtained in the optical pattern recognition and classification method of the present invention.

FIG. 10 is a diagram showing a recognition result for an unknown pattern using an experimentally obtained fuzzy AND operation and the accuracy of the recognition result in the optical pattern recognition and classification method of the present invention. .

FIG. 11 is a schematic configuration diagram of an optical system using a matched filter as another example used as an optical correlation processing device in the optical pattern recognition / classification method of the present invention.

FIG. 12 is a schematic configuration diagram of an optical system as still another example used as an optical correlation processing device in the optical pattern recognition / classification method of the present invention.

[Explanation of symbols]

 1, 3 pattern output means 2, 4 optical Fourier conversion means 5 light detection means 11 laser 12, 37 light flux 13 beam expander 4, 22, 39 beam splitter 35 liquid crystal light valve 16 pattern display device 21, 41 Fourier transform lens 31, 42 screen 32, 43 two-dimensional photoelectric conversion device 33, 51 pattern processing device 34, 38 mirror 36 light receiving device

Continuation of the front page (56) References JP-A-2-293829 (JP, A) JP-A-2-293828 (JP, A) JP-A 1-295233 (JP, A) (58) Fields investigated (Int) .Cl. ⁷ , DB name) G06T 7/00 G06F 9/44 554 JICST file (JOIS)

Claims (7)

(57) [Claims] 1. An optical pattern recognition / classification method, comprising:
A correlation output between a test pattern belonging to a class to be identified and classified and a plurality of reference patterns is taken a plurality of times, and a representative value of a set of obtained correlations and a parameter indicating a variation are obtained. After creating membership functions corresponding to the plurality of reference patterns for each class to be recognized and classified, each correlation output between the test pattern and the plurality of reference patterns, The membership values with the respective membership functions assigned to each of the classes to be recognized and classified are taken, and the smallest membership value of the obtained membership values or the membership value is obtained. The optical pattern is characterized in that an average value of the values corresponds to a degree belonging to the class to be recognized and classified of the test pattern.
Recognition classification method. 2. A correlation output between the plurality of reference patterns and a peak value of an auto-correlation output or a cross-correlation output between the test pattern and the plurality of reference patterns. 2. The optical pattern recognition and classification method according to claim 1, wherein: 3. A light-receiving area corresponding to a spread of an auto-correlation output or a cross-correlation output between the test pattern and each of the plurality of reference patterns. 2. The optical pattern recognition and classification method according to claim 1, wherein the total light amount or the average light amount is used. 4. A correlation output between the plurality of reference patterns and a peak value of an auto-correlation output or a cross-correlation output between the test pattern and each of the plurality of reference patterns. 2. The optical pattern recognition and classification method according to claim 1, wherein the total light amount or the average light amount in the light receiving range according to the spread of the correlation output is used. 5. An optical pattern recognition / classification method according to claim 1, wherein each correlation output with said plurality of reference patterns is obtained by using a matched filter. 6. A correlation output between each of the plurality of reference patterns is obtained by individually performing a joint Fourier transform between the test pattern and each of the reference patterns. The pattern is again optically individually Fourier transformed, or each joint pattern of the test pattern and each reference pattern is converted.
10. The method according to claim 8, wherein each of the obtained intensity patterns is collectively optically collectively subjected to the Fourier transform, and the obtained intensity pattern is collectively subjected to the Fourier transform. 5. An optical pattern recognition / classification method according to any one of items 1 to 4. 7. The correlation output of each of the plurality of reference patterns is obtained by superimposing each of the reference patterns on a test pattern represented by a light transmittance distribution or a light reflectance distribution. Incohi
2. The optical pattern recognition / classification method according to claim 1, wherein the light is irradiated with rent light, and the amount of light is reflected or transmitted.