Infrared image fusion for quality enhancement

This paper presents an approach for infrared image enhancement through fusion. Firstly, the infrared image is enhanced through histogram matching to enhance its dynamic range. A reference image with a good dynamic range, such as Cameraman, Lena, and Mandrill, is used in the histogram matching process. After that, the enhanced image is fused with the original image through curvelet fusion to inject much more details in the infrared image. The proposed approach achieves high quality of infrared image enhancement compared with different techniques.

A simplified Algorithm and Spiral Fractal in Transform Domain.. [DOI: 10.21203/rs.3.rs-1633883/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

This paper proposes a simplified fractal image compression algorithm which is implemented on a block by block basis. This algorithm achieves a compression ratio of up to 1:10 with a peak signal to noise ratio (PSNR) as high as 35dB. The idea of the proposed algorithm is based on the segmentation of the image, first, into blocks to setup reference blocks. The image is then decomposed again into block ranges and a search process is carried out to find the reference blocks with best match. The transmitted or stored values, after compression, are the reference block values and the indices of the reference block that achieves the best match. If there is no match, the average value of the block range is transmitted or stored instead. It proposes also the effect of using the spiral architecture instead of square block decomposition and searching in fractal compression. Comparisons with other systems; conventional square, the proposed simplified fractal compression and the standard JPEG are introduced. We applied these types of fractal compression systems on a video sequence. Also the effect of using the fractal image compression algorithms in transform domain is proposed. The image is transferred firstly to the transform domain. The Discrete Cosine Transform (DCT) and Wavelet Transform (DWT) are used. After transformation takes place the fractal algorithms is applied. Comparisons between three fractal algorithms; conventional square, spiral, and a simplified fractal compression are proposed. The comparisons are repeated in the two cases of transformation. The discrete wavelet is used also in this paper to increase the compression ratio in case of using the conventional method. We used the two dimension discrete wavelet to increase the compression ratio of the block domain pool transmission. We decompose the block domain by wavelet decomposition to two levels which gives a compression ratio of block domain transmission as high as 1:16. The advantages of the proposed algorithm are the simplicity of computation. We found that the using of spiral architecture in fractal compression, the produced or decoded image and so the video sequence visual quality are better than that produced with conventional square method and the proposed simplified system at the same compression ratio but with longer time consumed. We found also that all types of fractal compression system give better quality than the standard JPEG. We found also that the decoded images in case of using the wavelet transform are the best. And the in case of using DCT the decoded images has bad qualities.

Utilization of image interpolation and fusion in brain tumor segmentation

Brain tumor is a mass of anomalous cells in the brain. Medical imagining techniques have a vital role in the diagnosis of brain tumors. Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) techniques are the most popular techniques to localize the tumor area. Brain tumor segmentation is very important for the diagnosis of tumors. In this paper, we introduce a framework to perform brain tumor segmentation, and then localize the region of the tumor, accurately. The proposed framework begins with the fusion of MR and CT images by the Non-Sub-Sampled Shearlet Transform (NSST) with the aid of the Modified Central Force Optimization (MCFO) to get the optimum fusion result from the quality metrics perspective. After that, image interpolation is applied to obtain a High-Resolution (HR) image from the Low-Resolution (LR) ones. The objective of the interpolation process is to enrich the details of the fusion result prior to segmentation. Finally, the threshold and the watershed segmentation are applied sequentially to localize the tumor region, clearly. The proposed framework enhances the efficiency of segmentation to help the specialists diagnose brain tumors.

Classification of retinal images based on convolutional neural network

Automatic detection of maculopathy disease is a very important step to achieve high-accuracy results for the early discovery of the disease to help ophthalmologists to treat patients. Manual detection of diabetic maculopathy needs much effort and time from ophthalmologists. Detection of exudates from retinal images is applied for the maculopathy disease diagnosis. The first proposed framework in this paper for retinal image classification begins with fuzzy preprocessing in order to improve the original image to enhance the contrast between the objects and the background. After that, image segmentation is performed through binarization of the image to extract both blood vessels and the optic disc and then remove them from the original image. A gradient process is performed on the retinal image after this removal process for discrimination between normal and abnormal cases. Histogram of the gradients is estimated, and consequently the cumulative histogram of gradients is obtained and compared with a threshold cumulative histogram at certain bins. To determine the threshold cumulative histogram, cumulative histograms of images with exudates and images without exudates are obtained and averaged for each type, and the threshold cumulative histogram is set as the average of both cumulative histograms. Certain histogram bins are selected and thresholded according to the estimated threshold cumulative histogram, and the results are used for retinal image classification. In the second framework in this paper, a Convolutional Neural Network (CNN) is utilized to classify normal and abnormal cases.