Grayscale image feature extraction system

Abstract

The invention discloses a grayscale image feature extraction system, and the system comprises a wavelet image pyramid module which is used for carrying out the layer-by-layer decomposition of a grayscale image based on discrete wavelet transformation, extracting the low-frequency information representing the overall situation and the high-frequency information representing details in the image, and enabling the low-frequency information and the high-frequency information to serve as the multi-resolution representation of the image; the feature point detection module is used for detecting the position of the feature point in the image as the position information of the feature; and the feature narration module is used for performing main direction standardization on the neighborhood of the detected feature points, then generating corresponding narratives as narration information of the features, and finally outputting the positions of the feature points and the narratives as the features. The method can effectively solve the problem that it is difficult to capture details and global information of the image at the same time, and reduces the sensitivity of feature extraction to image noise.

Description

Technical Field

[0001] The present invention relates to the technical field of feature extraction, and in particular to a grayscale image feature extraction system. Background Art

[0002] Traditional image feature extraction methods mostly rely on pixel-level operations, such as analysis based on gradients, edges, or textures. However, these methods usually ignore the multi-scale characteristics of images and have difficulty effectively processing local details and global structures in images. Especially in complex natural images, traditional methods often find it difficult to capture image details and global information at the same time, resulting in incomplete feature expression. In addition, traditional methods are highly sensitive to noise and are easily disturbed by image noise, affecting the accuracy of feature extraction. The features generated by the current FAST feature point detection method do not have rotation invariance, resulting in the inability to correctly match the originally matched features after the image is rotated. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art and to provide a grayscale image feature extraction system that can effectively solve the problem of difficulty in capturing both image details and global information at the same time, while reducing the sensitivity of feature extraction to image noise and making the generated features rotationally invariant, thereby effectively improving the quality of feature matching.

[0004] To achieve the above object, the technical solution provided by the present invention is: a grayscale image feature extraction system, comprising:

[0005] The wavelet image pyramid module is used to decompose the grayscale image layer by layer based on discrete wavelet transform, extract the low-frequency information representing the global image and the high-frequency information representing the details in the image, and use this as the multiple resolution representation of the image;

[0006] A feature point detection module is used to detect the position of feature points in the image as feature position information;

[0007] The feature description module is used to normalize the main direction of the neighborhood of the detected feature point, generate the corresponding narrator as the feature description information, and finally output the position of the feature point and the narrator as the feature.

[0008] Furthermore, the wavelet image pyramid module specifically performs the following operations:

[0009] The grayscale image f(x,y) is represented by a wavelet image pyramid based on discrete wavelet transform, where the jth transform retains the image A with low-frequency information j (x, y) and the image H that retains high-frequency information j (x,y),V j (x,y),Dj The specific situation of (x,y) is as follows:

[0010]

[0011] In the formula, f(i,k) represents the grayscale value of the image f(x,y) at the coordinate (i,k), n and m represent the length and width of the image f(x,y), x and y represent the horizontal and vertical coordinates in the image, and · represents the multiplication operation. The image H j (x,y) represents the horizontal details, image V j (x,y) represents the vertical details, image D j (x,y) represents the diagonal details, g(·) represents the low-pass filter, and h h (·),h v (·),h d (·) respectively represent the corresponding images H j (x,y),V j (x,y),D j (x,y) high-pass filter, the specific type of filter is determined by the selected wavelet basis;

[0012] Then image A j (x,y),H j (x,y),V j (x,y),D j (x,y) and f(x,y) are input to the feature point detection module.

[0013] Furthermore, the feature point detection module specifically performs the following operations:

[0014] All pixels in all input images are judged. For each pixel p in the image f(x, y), the processing process is: select 16 pixels on the circle with it as the center for judgment, as shown in the following formula:

[0015]

[0016] In the formula, I p is the gray value of pixel p, I n is the gray value of the nth pixel on the ring, n = 1, 2, 3, ..., 16, t is an adjustable threshold, S n To judge the result;

[0017] When there are N′ consecutive pixels in the surrounding 16 pixels |S n When |≠0, the pixel point p is determined to be a feature point, denoted by p c , the coordinates of the feature point are marked as L c =(x,y);

[0018] For image A j (x,y),H j (x,y),V j (x,y) and D j The pixel points in (x, y) are judged as feature points, and the same processing process as the image f(x, y) is performed. The pixel points judged as feature points are recorded as p jc , the coordinates of the feature point are marked as L jc =(x,y), since each wavelet transform will shorten the length and width of the image by half, in order to make p jc Can be expressed on f(x,y), p jc The horizontal and vertical coordinates of the j times, denoted as p · jc ;

[0019] The obtained feature point p · jc With p c Compare to see if they are at the same pixel coordinates. If not, p · jc and p c All are retained, and the retained feature points are recorded as p l , the feature point p l The coordinates are marked as L l =(x,y); if yes, delete p · jc Keep p c , and the remaining feature points are recorded as p l , the feature point p l The coordinates are marked as L l =(x,y).

[0020] Furthermore, the feature description module specifically performs the following operations:

[0021] First, the detected feature point p l Normalization based on the main direction of the region is performed. Specifically, for each feature point, a region with a length and width of H pixels is selected around it as a window, and the region is defined as D. The partial derivatives of each pixel in the horizontal and vertical directions are calculated to obtain the gradient component G. x , G y :

[0022]

[0023] In the formula, G x Represents the partial derivative of the gray value I(x,y) at (x,y) with respect to x, G yRepresents the partial derivative of the gray value I(x,y) at (x,y) with respect to y;

[0024] Calculate the gradient magnitude m(x,y) and gradient direction θ(x,y) for each pixel:

[0025]

[0026] The gradient direction θ(x, y) is quantized to a set angle interval, and 360° is divided into M parts. In this way, the gradient direction of each pixel is mapped to a direction interval, and the gradient amplitude m(x, y) is used as the weight through weighted averaging. Each direction interval is represented by the cumulative sum of the gradient amplitudes of the directions included; the main direction θ m This is the direction where the cumulative sum of the gradient amplitude is the largest, that is, the interval corresponding to the maximum value:

[0027]

[0028] In the formula, i′ represents the i′th pixel point belonging to a certain direction interval;

[0029] Then the main direction θ m Normalize and rotate region D by -θ m After the degree, we get area D · , and based on D · The narrator is generated for the pixels within, as follows:

[0030] First, D · Divide into several sub-areas exist Calculate the gradient direction and gradient amplitude θ of the jth pixel nj (x,y),m nj (x,y), The gradient direction of each pixel in the image is mapped to M direction intervals, and the mean of the gradient direction and gradient amplitude in each direction interval is calculated. and As the local direction descriptor N of the direction interval am :

[0031]

[0032] Describe the M local directions as N am Arrange in a clockwise direction to get the sub-areas The local narrator N a :

[0033]

[0034] The local description sub-regions N aConcatenate from left to right and from top to bottom to form a complete narrative sub-N:

[0035]

[0036] Finally, the feature point p l The coordinates of L l =(x,y) and the descriptor N as the final feature.

[0037] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0038] 1. Use wavelet image pyramid to capture both image details and global information at the same time, and express features comprehensively. In addition, it is less sensitive to noise and is not easily disturbed by image noise, ensuring the accuracy of feature extraction and making the generated features rotationally invariant, effectively improving the quality of feature matching.

[0039] 2. Main direction normalization is added to the feature description module, so that the produced narrators are rotationally invariant, which improves the quality of feature description. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a framework diagram of the system of the present invention.

[0041] Figure 2 Schematic diagram of feature point detection.

[0042] Figure 3 Schematic diagram for normalization of directions. DETAILED DESCRIPTION

[0043] The present invention is further described in detail below in conjunction with embodiments and drawings, but the embodiments of the present invention are not limited thereto.

[0044] like Figures 1 to 3 As shown, this embodiment discloses a grayscale image feature extraction system, including:

[0045] The wavelet image pyramid module is used to decompose the grayscale image layer by layer based on discrete wavelet transform, extract the low-frequency information representing the global image and the high-frequency information representing the details in the image, and use this as the multiple resolution representation of the image;

[0046] A feature point detection module is used to detect the position of feature points in the image as feature position information;

[0047] The feature description module is used to normalize the main direction of the neighborhood of the detected feature point, generate the corresponding narrator as the feature description information, and finally output the position of the feature point and the narrator as the feature.

[0048] Specifically, the wavelet image pyramid module performs the following operations:

[0049] The grayscale image f(x,y) is represented by a wavelet image pyramid based on discrete wavelet transform, where the jth transform retains the image A with low-frequency information j (x, y) and the image H that retains high-frequency information j (x,y),V j (x,y),D j The specific situation of (x,y) is as follows:

[0050]

[0051] In the formula, f(i,k) represents the grayscale value of the image f(x,y) at the coordinate (i,k), n and m represent the length and width of the image f(x,y), x and y represent the horizontal and vertical coordinates in the image, and · represents the multiplication operation. The image H j (x,y) represents the horizontal details, image V j (x,y) represents the vertical details, image D j (x,y) represents the diagonal details, g(·) represents the low-pass filter, and h h (·),h v (·),h d (·) respectively represent the corresponding images H j (x,y),V j (x,y),D j (x,y) high-pass filter, the specific type of filter is determined by the selected wavelet basis;

[0052] Then image A j (x,y),H j (x,y),V j (x,y),D j (x,y) and f(x,y) are input to the feature point detection module.

[0053] Specifically, the feature point detection module performs the following operations:

[0054] All pixels in all input images are judged. For each pixel p in the image f(x, y), the processing process is: select 16 pixels on the ring with it as the center (see Figure 2 As shown in the following formula:

[0055]

[0056] In the formula, I p is the gray value of pixel p, I nis the gray value of the nth pixel on the ring, n = 1, 2, 3, ..., 16, t is an adjustable threshold, S n To judge the result;

[0057] When there are N′ consecutive pixels in the surrounding 16 pixels |S n When |≠0, the pixel point p is determined to be a feature point, denoted by p c , the coordinates of the feature point are marked as L c =(x,y);

[0058] For image A j (x,y),H j (x,y),V j (x,y) and D j The pixel points in (x, y) are judged as feature points, and the same processing process as the image f(x, y) is performed. The pixel points judged as feature points are recorded as p jc , the coordinates of the feature point are marked as L jc =(x,y), since each wavelet transform will shorten the length and width of the image by half, in order to make p jc Can be expressed on f(x,y), p jc The horizontal and vertical coordinates of the j times, denoted as p · jc ;

[0059] The obtained feature point p · jc With p c Compare to see if they are at the same pixel coordinates. If not, p · jc and p c All are retained, and the retained feature points are recorded as p l , the feature point p l The coordinates are marked as L l =(x,y); if yes, delete p · jc Keep p c , and the remaining feature points are recorded as p l , the feature point p l The coordinates are marked as L l =(x,y).

[0060] Specifically, the feature description module performs the following operations:

[0061] First, the detected feature point p lNormalization based on the main direction of the region is performed. Specifically, for each feature point, a region with a length and width of H pixels is selected around it as a window, and the region is defined as D. The partial derivatives of each pixel in the horizontal and vertical directions are calculated to obtain the gradient component G. x , G y :

[0062]

[0063] In the formula, G x Represents the partial derivative of the gray value I(x,y) at (x,y) with respect to x, G y Represents the partial derivative of the gray value I(x,y) at (x,y) with respect to y; calculates the gradient magnitude m(x,y) and gradient direction θ(x,y) of each pixel:

[0064]

[0065] The gradient direction θ(x, y) is quantized to a set angle interval, and 360° is divided into M parts. In this way, the gradient direction of each pixel is mapped to a direction interval, and the gradient amplitude m(x, y) is used as the weight through weighted averaging. Each direction interval is represented by the cumulative sum of the gradient amplitudes of the directions included; the main direction θ m This is the direction where the cumulative sum of the gradient amplitude is the largest, that is, the interval corresponding to the maximum value:

[0066]

[0067] In the formula, i′ represents the i′th pixel point belonging to a certain direction interval;

[0068] Then the main direction θ m Normalize and rotate region D by -θ m After the degree, we get area D · (See Figure 3 shown), and based on D · The narrator is generated for the pixels within, as follows:

[0069] First, D · Divide into several sub-areas exist Calculate the gradient direction and gradient amplitude θ of the jth pixel nj (x,y),m nj (x,y), The gradient direction of each pixel in the image is mapped to M direction intervals, and the mean of the gradient direction and gradient amplitude in each direction interval is calculated. and As the local direction descriptor N of the direction interval am :

[0070]

[0071] Describe the M local directions as N am Arrange in a clockwise direction to get the sub-areas The local narrator N a :

[0072]

[0073] The local description sub-regions N a Concatenate from left to right and from top to bottom to form a complete narrative sub-N:

[0074]

[0075] Finally, the feature point p l The coordinates of L l =(x,y) and the descriptor N as the final feature.

[0076] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A grayscale image feature extraction system, characterized in that: include: The wavelet image pyramid module is used to decompose the grayscale image layer by layer based on discrete wavelet transform, extract the low-frequency information representing the global image and the high-frequency information representing the details in the image, and use this as the multiple resolution representation of the image; A feature point detection module is used to detect the position of feature points in the image as feature position information; The feature description module is used to normalize the main direction of the neighborhood of the detected feature point, generate the corresponding narrator as the feature description information, and finally output the position of the feature point and the narrator as the feature.

2. A grayscale image feature extraction system according to claim 1, characterized in that: The wavelet image pyramid module specifically performs the following operations: The grayscale image f(x,y) is represented by a wavelet image pyramid based on discrete wavelet transform, where the jth transform retains the image A with low-frequency information j (x, y) and the image H that retains high-frequency information j (x,y),V j (x,y),D j The specific situation of (x,y) is as follows: In the formula, f(i,k) represents the grayscale value of the image f(x,y) at the coordinate (i,k), n and m represent the length and width of the image f(x,y), x and y represent the horizontal and vertical coordinates in the image, and · represents the multiplication operation. The image H j (x,y) represents the horizontal details, image V j (x,y) represents the vertical details, image D j (x,y) represents the diagonal details, g(·) represents the low-pass filter, and h h (·),h v (·),h d (·) respectively represent the corresponding images H j (x,y),V j (x,y),D j (x,y) high-pass filter, the specific type of filter is determined by the selected wavelet basis; Then image A j (x,y),H j (x,y),V j (x,y),D j (x,y) and f(x,y) are input to the feature point detection module.

3. A grayscale image feature extraction system according to claim 2, characterized in that: The feature point detection module specifically performs the following operations: All pixels in all input images are judged. For each pixel p in the image f(x, y), the processing process is: select 16 pixels on the circle with it as the center for judgment, as expressed by the following formula: In the formula, I p is the gray value of pixel p, I n is the gray value of the nth pixel on the ring, n = 1, 2, 3, ..., 16, t is an adjustable threshold, S n To judge the result; When there are N′ consecutive pixels in the surrounding 16 pixels |S n When |≠0, the pixel point p is determined to be a feature point, denoted by p c , the coordinates of the feature point are marked as L c =(x,y); For image A j (x,y),H j (x,y),V j (x,y) and D j The pixel points in (x, y) are judged as feature points, and the same processing process as the image f(x, y) is performed. The pixel points judged as feature points are recorded as p jc , the coordinates of the feature point are marked as L jc =(x,y), since each wavelet transform will shorten the length and width of the image by half, in order to make p jc Can be expressed on f(x,y), p jc The horizontal and vertical coordinates of the j times, denoted as p · jc ; The obtained feature point p · jc With p c Compare to see if they are at the same pixel coordinates. If not, p · jc and p c All are retained, and the retained feature points are recorded as p l , the feature point p l The coordinates are marked as L l =(x,y); if yes, delete p · jc Keep p c , and the remaining feature points are recorded as p l , the feature point p l The coordinates are marked as L l =(x,y).

4. A grayscale image feature extraction system according to claim 3, characterized in that: The feature description module specifically performs the following operations: First, the detected feature point p l Normalization based on the main direction of the region is performed. Specifically, for each feature point, a region with a length and width of H pixels is selected around it as a window, and the region is defined as D. The partial derivatives of each pixel in the horizontal and vertical directions are calculated to obtain the gradient component G. x , G y : In the formula, G x Represents the partial derivative of the gray value I(x,y) at (x,y) with respect to x, G y Represents the partial derivative of the gray value I(x,y) at (x,y) with respect to y; Calculate the gradient magnitude m(x,y) and gradient direction θ(x,y) for each pixel: The gradient direction θ(x, y) is quantized to a set angle interval, and 360° is divided into M parts. In this way, the gradient direction of each pixel is mapped to a direction interval, and the gradient amplitude m(x, y) is used as the weight through weighted averaging. Each direction interval is represented by the cumulative sum of the gradient amplitudes of the directions included; the main direction θ m This is the direction where the cumulative sum of the gradient amplitude is the largest, that is, the interval corresponding to the maximum value: In the formula, i′ represents the i′th pixel point belonging to a certain direction interval; Then the main direction θ m Normalize and rotate region D by -θ m After the degree, we get area D · , and based on D · The narrator is generated for the pixels within, as follows: First, D · Divide into several sub-areas exist Calculate the gradient direction and gradient amplitude θ of the jth pixel nj (x,y),m nj (x,y), The gradient direction of each pixel in the image is mapped to M direction intervals, and the mean of the gradient direction and gradient amplitude in each direction interval is calculated. and As the local direction descriptor N of the direction interval am : Describe the M local directions as N am Arrange in a clockwise direction to get the sub-areas The local narrator N a : The local description sub-regions N a Concatenate from left to right and from top to bottom to form a complete narrative sub-N: Finally, the feature point p l The coordinates of L l =(x,y) and the descriptor N as the final feature.

Images