Rapid area-of-interest detection method based on depth kernelized hashing

Abstract

The invention discloses a rapid area-of-interest detection method based on depth kernelized hashing and mainly aims to solve problems of low detection precision and low efficiency existing in an image area-of-interest detection method in the prior art. The method comprises steps that in a training process, to-be-trained data sets are classified into multiple categories which are inputted to a depth kernelized hashing supervised learning network framework to acquire corresponding hashing codes, fine tuning of network parameters is carried out according to a label information matrix till the optimal learning result is realized; in a test process, inputted test images are pre-processed, and binary codes are acquired through the trained depth kernelized hashing supervised learning network framework; the area-of-interest position of the image is determined according to a decision function and is marked, and area-of-interest detection and identification are accomplished. Through the method, area-of-interest detection analysis performance of the image can be effectively improved, an area-of-interest detection rate and system framework operation efficiency are improved, and the method can be applied to rapid detection and identification of breast image lumps.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a new rapid image target detection method, which can be applied to rapid detection and identification of medical breast image masses. Background technique [0002] As one of the most common malignant tumors in the world today, breast cancer has become the "number one killer" that seriously threatens women's health around the world. A large number of investigations and experiments have shown that early diagnosis and timely treatment are the best means and effective way to cure breast cancer. Mammography mammography examination is the most direct and efficient detection method for diagnosing breast diseases at present. As an important part of medical images, mammography images have extremely high application value due to their high resolution and strong contrast. and research value. [0003] Mammographic mass is one of the main forms of early breast cancer and is a...

AI Technical Summary

Problems solved by technology

The HOG feature used in this method is a kind of manual description feature. Although it has good sensitivity to gradient changes, it has poor descriptive power for texture information or spatial information, resulting in a high false detection rate in the mass detection results. Therefore, this method framework has shortcomings such as poor representation ability and over-fitting for the recognition and classification of medical images.

[0006] Although the above methods can complete breast image mass recognition, due to the limited ability of manual description features to image representation, the false detection rate or false positive rate is too high, and the optimal mass detection result cannot be obtained, and the solution speed of the model is slow. Target recognition and segmentation are less efficient

Images