Texture features for image classification and retrieval.

Smart cameras and image sensors are widely used in industrial processes, from the designing to the quality checking of the final product. Images generated by these sensors are at continuous risk of disclosure and privacy breach in the industrial Internet of Things (IIoT). Traditional solutions to secure sensitive data fade in IIoT environments because of the involvement of third parties. Blockchain technology is the modern-day solution for trust issues and eliminating or minimizing the role of the third party. In the context of the IIoT, we propose a permissioned private blockchain-based solution to secure the image while encrypting it. In this scheme, the cryptographic pixel values of an image are stored on the blockchain, ensuring the privacy and security of the image data. Based on the number of pixels change rate (NPCR), the unified averaged changed intensity (UACI), and information entropy analysis, we evaluate the strength of proposed image encryption algorithm ciphers with respect to differential attacks. We obtained entropy values near to an ideal value of 8, which is considered to be safe from brute force attack. Encrypted results show that the proposed scheme is highly effective for data leakage prevention and security.

https://www.mdpi.com/1099-4300/22/2/175/pdf

A Blockchain-Based Secure Image Encryption Scheme for the Industrial Internet of Things.

Dermatology is a one of major session of medicine that concerned with the diagnosis and treatment of skin diseases. Skin diseases are the most common form of disease in humans. Recently, many of researchers have advocated and developed the imaging of human vision or in the loop approach to visual object recognition. This research paper presents a development of a skin diseases diagnosis system which allows user to identify diseases of the human skin and to provide advises or medical treatments in a very short time period. For this purpose, user will have to upload an image of skin disease to our system and answer questions based on their skin condition or symptoms. It will be used to detect diseases of the skin and offer a treatment recommendation. This system uses technologies such as image processing and data mining for the diagnosis of the disease of the skin. The image of skin disease is taken and it must be subjected to various preprocessing for noise eliminating and enhancement of the image. This image is immediately segmentation of images using threshold values. Finally data mining techniques are used to identify the skin disease and to suggest medical treatments or advice for users. This expert system exhibits disease identification accuracy of 85% for Eczema, 95% for Impetigo and 85% for Melanoma.

/pdf/expert-system-for-diagnosis-of-skin-diseases-155p0rwvpi.pdf

Expert System For Diagnosis Of Skin Diseases

Problem statement: In this study a skin disease diagnosis system was developed and tested. The system was used for diagnosis of psoriases skin disease. Approach: Present study relied on both skin color and texture features (features derives from the GLCM) to give a better and more efficient recognition accuracy of skin diseases. We used feed forward neural networks to classify input images to be psoriases infected or non psoriasis infected. Results: The system gave very encouraging results during the neural network training and generalization face. Conclusion: The aim of this worked to evaluate the ability of the proposed skin texture recognition algorithm to discriminate between healthy and infected skins and we took the psoriasis disease as example.

Psoriasis Detection Using Skin Color and Texture Features

In the current age of technology, various diseases in the body are also on the rise. Tumours that cause more discomfort in the body are set to increase the discomfort of most patients. Patients experience different effects depending on the tumour size and type. Future developments in the medical field are moving towards the development of tools based on IoT devices. These advances will in the future follow special features designed based on multiple machine learning developed by artificial intelligence. In that order, an improved algorithm named Internet of Things-based enhanced machine learning is proposed in this paper. What makes it special is that it involves separate functions to diagnose each type of tumour. It analyzes and calculates things like the size, shape, and location of the tumour. Cure from cancer is determined by the stage at which we find cancer. Early detection of cancer has the potential to cure quickly. At a saturation point, the proposed Internet of Things-based enhanced machine learning model achieved 94.56% of accuracy, 94.12% of precision, 94.98% of recall, 95.12% of F1-score, and 1856 ms of execution time. The simulation is conducted to test the efficacy of the model, and the results of the simulation show that the proposed Internet of Things-based enhanced machine learning obtains a higher rate of intelligence than other methods.

/pdf/ioteml-an-internet-of-things-iot-based-enhanced-machine-2h9303qo.pdf

IOTEML: An Internet of Things (IoT)-Based Enhanced Machine Learning Model for Tumour Investigation

The retinal vasculature is composed of the arteries and veins with their tributaries which are visible within the retinal image. The segmentation and measurement of the retinal vasculature is of primary interest in the diagnosis and treatment of a number of systemic and ophthalmologic conditions. The accurate segmentati on of the retinal blood vessels is often an essential prerequisite step in the identification of retinal anatomy and pathology. In this study, we present an automated a pproach for blood vessels extraction using mathemat ical morphology. Two main steps are involved: enhancement operation is applied to the original retinal imag e in order to remove the noise and increase contrast of retinal blood vessels and morphology operations are employed to extract retinal blood vessels. This ope ration of segmentation is applied to binary image o f tophat transformation. The result was compared with ot her algorithms and give better results.

Blood vessels extraction using mathematical morphology

Skin recognition is used in many applications ranging from algorithms for face detection, hand gesture analysis, and to objectionable image filtering. In this work a skin recognition system was developed and tested. While many skin segmentation algorithms relay on skin color, our work relies on both skin color and texture features (features derives from the GLCM) to give a better and more efficient recognition accuracy of skin textures. We used feed forward neural networks to classify input textures images to be skin or non skin textures. The system gave very encouraging results during the neural network generalization face.

Skin Texture Recognition Using Neural Networks

Automatic lesion segmentation is an important part of computer-based image analysis of pigmented skin lesions. Currently, there is a great interest in th e development of Computer-Aided Diagnosis (CAD) systems for dermoscopic images. The segmentation step is one of the most important ones, since its accuracy determines the eventual success or failure of a CAD system. This study introduced new method of dermoscopic images segmentation. The preprocess was the filtering operation to dermoscopy image to rem ove most of difficulties facing the efficient segmentat ions, like a variety of lesion shapes, sizes, color , changes due to different skin types and textures and presence o f hairs. Segmentation based mainly on histogram thresholding. The enhancements of image achieved by using mathematical morphology in order to obtain better segmentation with smooth border and without any noise in the lesion region. The proposed method evaluated by using Hammoude Distance (HM) and the True Detection Rate (TDR). Also the proposed method is compared with other skin lesions segmentation methods such as Otsu, adaptive thresholding and fuzzy Cmeans. The accuracy of proposed method was 96.32%, which is highly promised result and dependable.

Automatic segmentation of skin lesions using histogram thresholding

Image encryption is one of the most methods of info rmation hiding. A novel secure encryption method fo r image encryption is presented in this study. The pr oposed algorithm based on using singular value decomposition SVD. In this study we start to scramb le the image data according to suggested keys (two sequence scrambling process with two different keys ) to finally create two different matrices. The dia gonal matrix from the SVD will be interchanged with the r esulted matrices. Another scrambling and diagonal matrices interchange will apply to increase the com plexity. The resulted two matrices combine to one matrix according to predefined procedure. The encrypted image is a meaningfull image. The suggested method tested with many images encryption and gives promised results.

Image encryption based on singular value decomposition

Detection and segmentation of faces from an image is a crucial problem that has gained importance, face detection and segmentation play the main role in the face recognition systems. There are many difficulties should be solved to make the face detection and segmentation algorithm successful. The face skin has special colors range as well as special textures that can be detected by using texture recognition algorithms which recognized skin from the background. In this paper we introduced a new method for face detection and segmentation based on face color, we uses the YCbCr color space as a method to segment image to many regions. Gray level co-occurrence matrix used to extract the important features represent the skin, and then Tamura texture used to remove all the non skin blobs which is recognized as skin by GLCM. The proposed algorithm tested with many images and it was successfully recognize the images with faces from images without faces. The proposed algorithm has high efficient in detected faces and segmented faces from the background. The accuracy of this algorithm more than 99% in detection faces and also segment its. The proposed algorithm forms a prerequisite for any practical verification system using face as the main attribute.

/pdf/detection-and-segmentation-of-human-face-49wi9oyw2f.pdf

Nidhal K. El Abbadi

Papers

Blood vessels extraction using mathematical morphology

Skin Texture Recognition Using Neural Networks

Automatic segmentation of skin lesions using histogram thresholding

Image encryption based on singular value decomposition

Detection and Segmentation of Human Face