With the development of machine learning for decades, there are still many problems unsolved, such as image recognition and location detection, classification, generation, speech recognition, natural language processing so on. In field deep research, research on classification has always been most basic, traditional urgent direction. At same time, computer intelligent technology is also conduci...

Household garbage images are usually faced with complex backgrounds, variable illuminations, diverse angles, and changeable shapes, which bring a great difficulty in image classification. Due to the ability discover problem-specific features, deep learning especially convolutional neural networks (CNNs) have been successfully widely used for representation learning. However, available stable ho...

Assessment of visual encryption video and image content requires a reliable estimation recognizability low quality. As pointed out in the literature, current methods are insufficient research into this topic, as well relation between quality recognizability, is still lacking. This lack primarily due to data. To improve on status-quo we have taken database performed subjective evaluation subset ...

Abstract Welding technology is an important link in shipbuilding, and ultrasonic diffraction time difference method one of its inspection means, but the identification TOFD image still mainly relies on manual evaluation. In this paper, order to solve problems low accuracy unbalanced categories defect recognition existing automatic research, by reclassifying defects into primary defects, seconda...