A picture quality detection method based on machine learning

Abstract

The invention discloses a picture quality detection method based on machine learning, and belongs to the field of picture recognition, and the method comprises the following steps: collecting data ofa problematic picture; performing analysis processing and classification processing according to the collected picture data; establishing a picture preliminary image quality comparison detection library for the pictures subjected to analysis processing and classification processing; extracting image quality characteristics of each image in the preliminary image quality library; establishing an image quality feature library according to the image quality features of the image; detecting the image according to the image quality feature library and the preliminary image quality library; detectingoutput results. The method comprises the following steps of: extracting feature learning from previous images with image quality function problems by using a machine learning method, quickly positioning which kind of problems belong to, performing feature learning on the images with the image quality function problems by using a deep learning technology, and classifying the learned features to obtain a deep learning model; and judging the image quality function picture of the camera by using the deep learning model and outputting a result.

Description

【Technical field】 [0001] The invention relates to the field of picture recognition, in particular to a machine learning-based picture quality detection method. 【Background technique】 [0002] With the development of society, people are more and more fond of taking pictures, but due to the difference of each person's photographing techniques, there are various problems in the pictures taken, which often cannot meet people's needs. With the development of Internet technology, pictures are widely used in more and more web pages and applications because of their advantages of intuitive expression and rich content compared with text. But the existing cameras can only take pictures of the pictures, and fail to automatically classify the pictures or classify the exposure pictures or choose handsomely, so that people can check and select each one after taking the pictures, which greatly improves the quality of the pictures. increased the workload of people. [0003] With the accel...

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to disclose a machine learning-based picture quality detection method to solve the technical problem that the existing exposed picture quality cannot be automatically screened and classified

Images