A Trademark Retrieval Method Based on Similar Region Detection and Segmentation
A technology of similar regions and trademarks, applied in the field of information retrieval, can solve problems such as difficulty in dealing with trademark applications and infringement cases, decline in examination accuracy and quality, and increase in examination difficulty, achieving improved accuracy, excellent search results, and reduced workload amount of effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0031] A trademark retrieval method based on similar region detection and segmentation, comprising the following steps:
[0032] 1. Obtain all sample trademarks;
[0033] 2. Extract the features of the image of the sample trademark;
[0034] Prewitt operator edge detection
[0035] The Prewitt operator is an edge detection of a first-order differential operator. It uses the gray level difference between the upper and lower pixels and the left and right adjacent points to reach the extreme value at the edge to detect the edge, remove part of the false edge, and have a smoothing effect on the noise. The principle is to perform neighborhood convolution with the image using two direction templates in the image space, one of which detects horizontal edges, and the other detects vertical edges.
[0036] For example, for a digital image f(x, y), the Prewitt operator is defined as follows:
[0037] G(i)=|[f(i-1, j-1)+f(i-1, j)+f(i-1, j+1)]-[f(i+1, j-1) +f(i+1, j)+f(i+1, j+1)]|
...
Embodiment 2
[0078] A trademark retrieval method based on similar region detection and segmentation, comprising the following steps:
[0079] 1. Obtain all sample trademarks;
[0080] 2. Extract the features of the image of the sample trademark;
[0081] Prewitt operator edge detection
[0082] The Prewitt operator is an edge detection of a first-order differential operator. It uses the gray level difference between the upper and lower pixels and the left and right adjacent points to reach the extreme value at the edge to detect the edge, remove part of the false edge, and have a smoothing effect on the noise. The principle is to perform neighborhood convolution with the image using two direction templates in the image space, one of which detects horizontal edges, and the other detects vertical edges.
[0083] For example, for a digital image f(x, y), the Prewitt operator is defined as follows:
[0084] G(i)=|[f(i-1, j-1)+f(i-1, j)+f(i-1, j+1)]-[f(i+1, j-1) +f(i+1, j)+f(i+1, j+1)]|
...
Embodiment 3
[0125] A trademark retrieval method based on similar region detection and segmentation, comprising the following steps:
[0126] 1. Obtain all sample trademarks;
[0127] 2. Extract the features of the image of the sample trademark;
[0128] Laplacian operator edge detection
[0129] The Laplacian operator is based on the second-order differential operator, which uses the principle of the second-order differential zero-crossing point to extract boundary points. In the process of algorithm implementation, the 3x3 convolution kernel operation is also used to select the appropriate threshold to extract the edge. The Laplacian operator is expressed as a template as follows:
[0130] Laplacian operator template:
[0131]
[0132] Its extended template:
[0133]
[0134] 3. Based on the extracted features, establish an image feature database for the image part of the sample trademark;
[0135] 4. Obtain the trademark to be tested;
[0136] 5. According to the same steps...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More