In this article a new combination of image segmentation techniques including K-means clustering, watershed transform, region merging and growing algorithm was proposed to segment computed tomography(CT) and magnetic resonance(MR) medical images.The first stage in the proposed system is "preprocessing" for required image enhancement, cropped, and convert the images into .mat or png ...etc image file formats then the image will be segmented using combination methods (clustering , region growing, and watershed, thresholding). Some initial over-segmentation appears due to the high sensitivity of the watershed algorithm to the gradient image intensity variations. Here, K-means and region growing with correct thresholding value are used to overcome that over segmentations. In our system the number of pixels of segmented area is calculated which is very important for medical image analysis for diseases or medicine effects on affected area of human body also displaying the edge map.The results show that using clustering method output to region growing as input image, gives accurate and very good results compare with watershed technique which depends on gradient of input image, the mean and the threshold values which are chosen manually. Also the results show that the manual selection of the threshold value for the watershed is not as good as automatically selecting, where data misses may be happen.
Image compression is one of the data compression types applied to digital images in order to reduce their high cost for storage and/or transmission. Image compression algorithms may take the benefit of visual sensitivity and statistical properties of image data to deliver superior results in comparison with generic data compression schemes, which are used for other digital data. In the first approach, the input image is divided into blocks, each of which is 16 x 16, 32 x 32, or 64 x 64 pixels. The blocks are converted first into a string; then, encoded by using a lossless and dictionary-based algorithm known as arithmetic coding. The more occurrence of the pixels values is codded in few bits compare with pixel values of less occurrence through the sub intervals between the range 0 and 1. Finally, the stream of compressed tables is reassembled for decompressing (image restoration). The results showed a compression gain of 10-12% and less time consumption when applying this type of coding to each block rather than the entire image. To improve the compression ratio, the second approach was used based on the YCbCr colour model. In this regard, images were decomposed into four sub-bands (low-low, high-low, low-high, and high-high) by using the discrete wavelet transform compression algorithm. Then, the low-low sub-band was transmuted to frequency components (low and high) via discrete wavelet transform. Next, these components were quantized by using scalar quantization and then scanning in a zigzag way. The compression ratio result is 15.1 to 27.5 for magnetic resonance imaging with a different peak signal to noise ratio and mean square error; 25 to 43 for X-ray images; 32 to 46 for computed tomography scan images; and 19 to 36 for magnetic resonance imaging brain images. The second approach showed an improved compression scheme compared to the first approach considering compression ratio, peak signal to noise ratio, and mean square error.
Face detection is one of the important applications of biometric technology and image processing. Convolutional neural networks (CNN) have been successfully used with great results in the areas of image processing as well as pattern recognition. In the recent years, deep learning techniques specifically CNN techniques have achieved marvellous accuracy rates on face detection field. Therefore, this study provides a comprehensive analysis of face detection research and applications that use various CNN methods and algorithms. This paper presents ten of the most recent studies and illustrate the achieved performance of each method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.