Quantization table, image compression processing method, device, terminal and image search system
A technology of a processing device and a processing method, which is applied in the field of communication, can solve the problem that the bit number of query images cannot meet the transmission performance of low-performance mobile devices, and achieve the effects of maintaining the accuracy of results, improving operability, and increasing compression rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach
[0080] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are the Some, but not all, embodiments are invented. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0081] The present invention mainly provides an image compression method and an image search system. The method and the system can improve the compression rate of the query picture under the condition that the compressed feature quantity complies with the JPEG code stream standard, and maintain the accuracy rate of the retrieval result of the compressed picture on the serve...
no. 1 example
[0083] Figure 11 A flow chart of steps for obtaining an optimized quantization table provided by Embodiment 1 of the present invention is shown. combine Figure 11 As shown, the method for obtaining the optimized quantization table in this embodiment is as follows.
[0084] 1101. Set the quantization value in the initial quantization table according to a preset formula to reduce the problem space.
[0085] Generally, the JPEG compression process uses its recommended default quantization table to quantize the DCT coefficients. The default quantization table recommended by the JPEG standard is as follows: figure 1 shown. The starting goal of the design of the JPEG default quantization table is to maintain the sensory effect of human vision, and no special optimization is made for visual search or image characteristics. In order to maintain image characteristics while further improving compression performance, it is necessary to reset the quantization table. However, the q...
no. 2 example
[0117] Figure 12 A flow chart of the steps of the image compression method provided by Embodiment 2 of the present invention is shown. combine Figure 12 As shown, the image compression method in this embodiment is as follows.
[0118] 1201. Divide the target image into several 8*8 sub-blocks, and perform discrete cosine transform (DCT) on each 8*8 image block.
[0119] It can be understood that the DCT transformation presents the pixels in the target image and the rules between pixels, which is more convenient for compressing the target image. For example, after the target image is transformed from the spatial domain to the frequency domain after DCT transformation, the low-frequency components in the spectral information correspond to the areas where the gray value changes slowly in the target image, while the high-frequency components in the spectral information correspond to the gray areas in the image. Areas with drastic changes in degree values (such as information...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More