Research of animals image semantic segmentation based on deep learning

Abstract

It is imperative for us to develop the technology of image semantic segmentation with the increasing demand in the image processing. Nowadays, the development of deep learning is of great significance to the improvement of image segmentation. Furthermore, the paper discussed the relationship between image semantic segmentation and animal image research based on the actual situation, and found that animal image processing technology plays a more important role in the field of protecting precious animals. The end-to-end network training of this paper is consisted of Fully Convolutional Network (FCN) for the front end and Conditional Random Fields as Recurrent Neural Networks (CRF-RNN) for the back end via comparing a variety of research methods. The experiments achieved desired outcome for the semantic segmentation of animal images by utilizing Caffe deep learning framework and explained the implementation details from the aspects of training and testing. KEYWORDS Caffe, CRF-RNN, FCN, image semantic segmentation INTRODUCTIONTraditionally, the segmentation of the image is only directly on the surface layer, such as the appearance features based on texture, color, and shape, and they are separated after aggregating the similar features. Among them, the segmentation method based on regions, because the selection of seed points will lead to low efficiency of the algorithm, the segmented results have a certain flaw and can not reach the expected effect. However, the histogram-based threshold segmentation method ignores certain image space information, and it is very likely to segment a discontinuous and meaningless regions, making the segmentation result less satisfying. Therefore, with the demand for image segmentation technology, the semantic segmentation is indispensable.In semantic segmentation, the method of deep learning can be well escaped from the traditional processing methods, and the limitation of using only the underlying features is eliminated, making process in the level of understanding for image. The deep learning framework of Caffe 1 can handle semantic segmentation well. As the number of treasured animals continues to decline, the application of science and technology to protect them is imminent. In particular, it is necessary to collect a set of quality and distinctive animal image data for a specific animal, and the collection of a large number of data sets depends not only on human resources but also requires the support of the relevant sensors, cameras, and other hardware in the wild places it can automatically detect in the field or other places. One solution is to establish a corresponding index for the existing animal picture database. For the protected animal, it can use image processing technology to quickly identify for these animals, and then semantic segmentation is exploited to make a good recognition of animal images. This will not only increase the efficiency of the staff, but reduce the situation in which Concurrency Computat Pract Exper. 2020;32:e4892. wileyonlinelibrary.com/journal/cp...

An online log template extraction method based on hierarchical clustering

“…The method of using the source code for log parsing, although highly accurate, is generally not available, because ordinary engineers cannot get the source code generating logs. In the field which researches of log analysis, a great deal of researchers did a lot of related works about detecting anomaly [21][22][23][24][25][26][27][28][29][30][31]. The most important feature of the abovementioned clustering-based log template extraction method is that when the similarity function is established.…”

Convergence of deep machine learning and parallel computing environment for bio‐engineering applications

“…Liu et al have discussed the relationship between image semantic segmentation and animal image research based on the actual situation, and found that animal image processing technology plays a more important role in the field of protecting precious animals. The end‐to‐end network training of this paper has consisted of Fully Convolutional Network (FCN) for the front end and Conditional Random Fields as Recurrent Neural Networks (CRF‐RNN) for the back end via comparing a variety of research methods.…”

Image semantic segmentation method based on GAN network and ENet model

“…© 2021 The Authors. The Journal of Engineering published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology problems such as large parameters and complex calculations due to the influence of network depth [12,13]. This leads to the problem of insufficient real-time performance for image segmentation.…”

“…The emergence of deep learning (DL) has opened up a new situation for the problem of image target segmentation and recognition, and has excellent performance for the recognition of a variety of small‐scale data sets [11]. At the same time, it is still necessary to see that traditional DL network models have problems such as large parameters and complex calculations due to the influence of network depth [12, 13]. This leads to the problem of insufficient real‐time performance for image segmentation.…”