JPH0344349B2 - - Google Patents

Description

[Detailed description of the invention]

[Industrial Application Field] The present invention is directed to a digital image that realizes high-speed labeling processing for a large number of connected regions by dividing an image region and deleting redundant connection relationships within and between partial images. Concerning labeling methods for regions. In image processing, there is a method of attaching a label to each pixel and performing the processing. Since the number of pixels involved in attaching such labels is enormous, it is important for high-speed image processing to be able to perform labeling processing at high speed. [Prior art] Conventional methods for labeling image areas include:
First, a provisional label is attached to the entire target image, the connection relationships of the provisional labels are detected and organized, the provisional labels are clustered, and the provisional labels subjected to this processing are updated to give the desired label. There are methods to enforce this. [Problem to be solved by the invention] In the above-mentioned method, it is essential to organize the connection relationships of provisional labels, but the amount of calculation required for this is equal to the maximum number of provisional labels included in the image area. The amount of calculation is proportional to the square of . Because such an amount of calculation is required, high-speed processing cannot be expected, especially when an image including a large number of connected regions must be processed. [Means for Solving the Problems] The present invention provides a labeling method for digital image areas that solves the above-mentioned problems as much as possible. provisional labeling means for sequentially adding a provisional label to each region within each unit image; and intra-partial image connections for detecting a connection relationship between an arbitrary provisional label in each partial image and provisional labels in its vicinity. relationship detection means; inter-partial image connection relation detection means for detecting connection relations of provisional labels between adjacent partial images; and provisional labels for deleting overlapping connection relations of provisional labels for each partial image and for each partial image. The present invention is comprised of organizing means and means for detecting all provisional labels belonging to each area in the input digital image based on the organized connection relationships and updating the provisional labels. [Operation] According to the method of the present invention, provisional labels are sequentially added to each region within each unit image for each partial image,
The connection relationship between any temporary label in each partial image and its neighboring temporary label and the connection relationship of circuit labels between adjacent partial images are detected, and each partial image of the detected connection relationship is detected. The connection relationships of duplicate provisional labels that exist for each image and each partial image are deleted, and all provisional labels belonging to each area in the input digital image are detected based on the organized connection relationships, and each processing area is I try to label it. As a result, the amount of computation required for labeling processing can be significantly reduced, and the speed of labeling processing can be significantly increased. [Embodiments] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. FIG. 1 shows an embodiment of the invention. In this figure, reference numeral 10 denotes a provisional labeling unit, which scans a square-shaped window as shown in Fig. 2 over partial images that are sequentially input, and generates labels as shown in Fig. 3. Do an extension. Such label generation and extension processing itself is a known method. Then, the connection relationship detection unit (within the partial image) 11 operates according to the logic shown in FIG. 4 to detect the connection relationship between any provisional label in the partial image and the provisional label adjacent thereto. At the same time, the connection relationship detection unit (between partial images) 12 operates according to the logic shown in FIG. 5, and detects the connection relationship of each provisional label between partial images at the boundary of each partial image. FIG. 6 shows an example of an image and detected connection relationships after the provisional labeling process as described above has been performed. The connection relationship data detected by the intra-partial image connection relationship detection unit 11 (a-1 in FIG. 7) is supplied to the provisional label organizing units 13 ₁ to 13 ₄ , and the overlapping portions of connection relationships indicated by these data ( The underlined connection-related portions in FIG. 7) are deleted as redundant portions, and an organized provisional label is output (as shown in b-1 in FIG. 7). In addition, the connection relationship detection unit 1 between partial images
Similarly, the connection relationship data detected in step 2 (a _- 2 in FIG.
4 ₃ , the duplicate connection relationship is deleted (as shown in b-2 in FIG. 7), and a sorted provisional label is output. These organizing sections 13 ₁ to 13 ₄ ; 14 ₁ to 14 ₃
From the organized connection relationships output from the 8th Direct connection label detection unit 15 ₁ to 1 uses a direct connection table as shown in the figure.
5 Create with ₄ . In FIG. 8, a partial image area identification code is added to the temporary label in each partial image to distinguish the labels. The direct connection table is supplied to the label tracking unit 16, which searches for labels based on the contents of the direct connection table and detects all provisional labels that are directly or indirectly connected (this is called clustering). . This allows all temporary labels contained within each area to be detected. The provisional label updating unit 17 that responds to the output of this label tracking result changes the provisional labels attached to the small regions belonging to the regions in each partial image that are to be the same region in the image region after provisional labeling into the same region. The label is updated to a new label (FIG. 9) and the labeled image area data is output. An example of how the amount of calculation can be reduced when dividing the image area and organizing the temporary labels as described above is as follows. That is, the size of the image is l×l, the maximum value of its provisional label is Lm, the case where the above division is not performed is (A), and the case where division is performed (however, it is divided into 8 parts) is (A). B), the differences between these two are as shown in the table below.

〔Effect of the invention〕

As explained above, according to the present invention, it is possible to provide a means for significantly reducing the amount of calculation required for labeling processing, and to contribute to speeding up processing.

[Brief explanation of drawings]

FIG. 1 is a diagram showing an embodiment of the present invention, FIG. 2 is a diagram showing an image scanning mode, FIG. 3 is a diagram showing a list of relationships between label generation and extension processing, and FIG. Figure 5 is a diagram illustrating the processing logic for detecting connection relationships within partial images. Figure 5 is a diagram illustrating the logic for detecting connection relationships between partial images. Figure 6 is the image and detection after provisional labeling processing. Figure 7 is a diagram illustrating the process of deleting duplicated parts of connection relationships, Figure 8 is a diagram showing part of an example of creating a direct connection table, Figure 9 is a temporary label FIG. 3 is a diagram showing a state in which a label is updated to the same new label. In FIG. 1, 10 is a provisional labeling section;
1 is an intra-partial image connection relationship detection unit, 12 is an inter-partial image connection relationship detection unit, 13 ₁ to 13 ₄ ; 14 ₁ to 14 ₃ is a provisional label organizing unit, 15 ₁ to 15 ₄ is a direct connection label detection unit, 16 is label tracking department, 17
is the temporary label update section.

Claims (1)

[Claims] 1. A provisional labeling means that sequentially adds a provisional label to each region within each unit image for each partial image of an input digital image, and a connection between an arbitrary provisional label in each partial image and provisional labels in its vicinity. intrapartial image connection relation detection means for detecting a relationship; interpartial image connection relation detection means for detecting a connection relation of provisional labels between adjacent partial images; The present invention is configured to include provisional label organizing means for deleting connection relationships, and means for detecting all provisional labels belonging to each area in an input digital image based on the organized connection relationships and updating the provisional labels. A labeling method for digital image areas characterized by: