Face recognition technology has become an important quantitative examination method in the field of forensic identification of human images. However, face image quality affects the recognition performance of face recognition systems. Existing research on the effects of face image denoising and enhancement methods on the face recognition performance are typically based on facial images with manually synthesized noises rather than the noises under natural environmental corruption, and their studied face recognition techniques are limited on the traditional face recognition algorithms rather than state-of-the-art convolutional neural network based face recognition methods. In this work, face image materials from 33 real cases in forensic identification of human images were collected for quantitative analysis of the effects of face image denoising and enhancement methods on the deep face recognition performance of the MXNet system architecture based face recognition system. The results show that face image quality has a significant effect on the recognition performance of the face recognition system, and the image processing techniques can enhance the quality of face images, and then improve the recognition precision of the face recognition system. In addition, the effects of the Gaussian filtering are better than the self-snake model based image enhancement method, which indicates that the image denoising methods are more suitable for performance improvement of the deep face recognition system rather than the image enhancement techniques under the application of the practical cases.

Image processing effects on the deep face recognition system.

Objective: Smartphone industry is growing day by day.According to studies, maximum smartphone users watch videos on their smartphones.With the time, android operating system is becoming popular due to the applications which are based on android SDKsthat attract the attention of the mobile phone users. Methods: However, with the increase of its popularity video editing in android devices is becoming a complex task for many reasons as well like poor video quality after editing, slow editing process, editing tool crashes while editing etc. There is a need of an attractivetool and an efficient environmentto deal with such complex tasks. Findings: This study discusses the novel and easy-to-use interface of video editing in android devices. The developed tool can perform video encoding which generates number of frames per second. We have applied image processing techniques to add images or text to any frame of video and can apply different effects like covers, sepia, gamma, rotation, snow. Then the tool can regenerate video from the frames produced after editing and application of various effects. Application:The resultant video will be quality conscious and can be generated in multiple formats like MP4, 3GP, and MOV reliably. 
Keywords: Android Phones, Digital Video, Image Processing, Smartphones, Video Processing, Video Editing

/pdf/an-efficient-video-editing-application-for-android-based-3gojnmiaxb.pdf

An Efficient Video Editing Application for Android based Technologies

Cloud enhancement of NOAA multispectral images by using independent component analysis and principal component analysis for sustainable systems

Finger vein biometric technology has gained a lot of popularity over recent years. This is primarily due to the increased security and reliability level that comes with its non-intrusive nature. Non-intrusiveness became inevitable due to the pandemic of COVID-19. This paper introduces a unique and lightweight image enhancement method for person identification using Convolutional Neural Networks (CNN). As pre-processing steps, Contrast Limited Adaptive Histogram Equalization (CLAHE) followed by gamma correction is applied. Afterward, the image is sharpened and then passed through the median filter. These steps are followed by applying power law and contrast adjustment. As a final step, CLAHE is used yet again to bring out the enhanced vascular structure. The method was appraised using the four different openly accessible databases. These are regarded as the most challenging available finger vein database-s by many researchers. For recognition purposes, CNN was used with transfer learning. Transfer learning is implemented by modifying the 13 convolutional layers of VGG-16. The proposed model architecture also includes five max-pooling layers, one ReLU, and one Softmax layer. It is observed that with transfer learning, the accuracy could have reached up to 99% on finger-vein recognition on the experimented dataset, thus proved to be a highly accurate approach for finger vein recognition.

Finger-vein recognition using a novel enhancement method with convolutional neural network

X-ray images play an important role in providing physicians with satisfactory information correlated to fractures and diseases; unfortunately, most of these images suffer from low contrast and poor quality. Thus, enhancement of the image will increase the accuracy of correct information on pathologies for an autonomous diagnosis system. In this paper, a new approach for low-contrast X-ray image enhancement based on brightness adjustment using a fuzzy gamma reasoning model (FGRM) is proposed. To achieve this, three phases are considered: pre-processing, Fuzzy model for adaptive gamma correction (GC), and quality assessment based on blind reference. The proposed approach’s accuracy is examined through two different blind reference approaches based on statistical measures (BR-SM) and dispersion-location (BR-DL) descriptors, supported by resulting images. Experimental results of the proposed FGRM approach on three databases (cervical, lumbar, and hand radiographs) yield favorable results in terms of contrast adjustment and providing satisfactory quality images.

Low-contrast X-ray enhancement using a fuzzy gamma reasoning model

Image enhancement is considered as one of the most important techniques in image research. The main aim of image enhancement is to enhance the quality and visual appearance of an image, or to provide a better transform representation for future automated image processing. Many images like medical images, satellite, aerial images and also real life photographs suffer from poor and bad contrast and noise. It is necessary to enhance the contrast and remove the noise to increase image quality. One of the most important stages in medical images detection and analysis is Image Enhancement Techniques. It improves the clarity of images for human viewing, removing blurring and noise, increasing contrast, and revealing details. These are examples of enhancement operations. The enhancement technique differs from one field to another depending on its objective. The existing techniques of image enhancement can be classified into two categories: Spatial Domain and Frequency Domain Enhancement. In this paper, we present an overview of Image Enhancement Processing Techniques in Spatial Domain. More specifically, we categorise processing methods based representative techniques of Image enhancement. Thus the contribution of this paper is to classify and review Image Enhancement Processing Techniques as well as various noises has been applied to the image. Also we applied various filters to identify which filter is efficient in removing particular noises. This is identified by comparing the values obtained in PSNR and MSE values. From this we can get an idea about which filters is best for removing which types of noises. It will be useful and easier to detect the filters for future research.

P. Janani

Papers

Image Enhancement Techniques: A Study