MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

Computer and Robot Vision Vol. 1, by R.M. Haralick and Linda G. Shapiro, Addison-Wesley, 1992, ISBN 0-201-10887-1.

Computer and Robot Vision

As the next-generation manufacturing system, intelligent manufacturing enables better quality, higher productivity, lower cost, and increased manufacturing flexibility. The concept of sustainability is receiving increasing attention, and sustainable manufacturing is evolving. The digital twin is an emerging technology used in intelligent manufacturing that can grasp the state of intelligent manufacturing systems in real-time and predict system failures. Sustainable intelligent manufacturing based on a digital twin has advantages in practical applications. To fully understand the intelligent manufacturing that provides the digital twin, this study reviews both technologies and discusses the sustainability of intelligent manufacturing. Firstly, the relevant content of intelligent manufacturing, including intelligent manufacturing equipment, systems, and services, is analyzed. In addition, the sustainability of intelligent manufacturing is discussed. Subsequently, a digital twin and its application are introduced along with the development of intelligent manufacturing based on the digital twin technology. Finally, combined with the current status, the future development direction of intelligent manufacturing is presented.

/pdf/digital-twin-based-sustainable-intelligent-manufacturing-a-32gjodfp5s.pdf

Digital twin-based sustainable intelligent manufacturing: a review

Objective To (1) map how different stakeholders understand telehealth and telecare technologies and (2) explore the implications for development and implementation of telehealth and telecare services. Design Discourse analysis. Sample 68 publications representing diverse perspectives (academic, policy, service, commercial and lay) on telehealth and telecare plus field notes from 10 knowledge-sharing events. Method Following a familiarisation phase (browsing and informal interviews), we studied a systematic sample of texts in detail. Through repeated close reading, we identified assumptions, metaphors, storylines, scenarios, practices and rhetorical positions. We added successive findings to an emerging picture of the whole. Main findings Telehealth and telecare technologies featured prominently in texts on chronic illness and ageing. There was no coherent organising vision. Rather, four conflicting discourses were evident and engaged only minimally with one another's arguments. Modernist discourse presented a futuristic utopian vision in which assistive technologies, implemented at scale, would enable society to meet its moral obligations to older people by creating a safe ‘smart’ home environment where help was always at hand, while generating efficiency savings. Humanist discourse emphasised the uniqueness and moral worth of the individual and tailoring to personal and family context; it considered that technologies were only sometimes fit for purpose and could create as well as solve problems. Political economy discourse envisaged a techno-economic complex of powerful vested interests driving commodification of healthcare and diversion of public funds into private business. Change management discourse recognised the complicatedness of large-scale technology programmes and emphasised good project management and organisational processes. Conclusion Introduction of telehealth and telecare is hampered because different stakeholders hold different assumptions, values and world views, ‘talk past’ each other and compete for recognition and resources. If investments in these technologies are to bear fruit, more effective inter-stakeholder dialogue must occur to establish an organising vision that better accommodates competing discourses.

For peer review only The organising vision for telehealth and telecare: discourse analysis

The machine learning and artificial intelligence play a vital role to solve the challenging issues in Clinical imaging. The machine learning and artificial intelligence ease the daily life of both medical practitioner and patient's. Nowadays, the automatic system is designed with high accuracy to perceive abnormality in bone X-ray images. To achieve high accuracy system has less resource available image pre-processing tools are used to enhance the medical images quality. The image pre-processing involves the process like noise removal and contrast enhancement which provides instantaneous abnormality diagnosis system. The Gray Level Co-occurrence Matrix (GLCM) texture features are widely used in image classification problems. GLCM represents the second-order statistical information of gray levels between neighboring pixels in an image[1]. In the paper, we implemented different machine learning approaches to classify the bone X-ray images of MURA (musculoskeletal radiographs) dataset into fractures and no fracture category. The four different classifiers LBF SVM (Radial Basis Function support vector machine), linear SVM, Logistic Regression and Decision tree are used for abnormality detection. The performance evaluation of the above abnormality detection in X-ray images is performed by using five statistical parameters such as Sensitivity, Specificity, Precision, Accuracy and F1 Score, which shows significant improvement.

GLCM Based Feature Extraction and Medical X-RAY Image Classification using Machine Learning Techniques

Edges of an image are considered a type of crucial information that can be extracted by applying detectors with different methodology. Edge detection is a basic and important subject in computer vision and image processing In this Paper we discuss several Digital Image Processing Techniques applied in edge feature extraction. Firstly, Linear filtering of Image is done is used to remove noises from the image collected. Secondly, some edge detection operators such as Sobel, Log edge detection, canny edge detection are analyzed and then according to the simulation results, the advantages and disadvantages of these edge detection operators are compared. It is shown that the canny operator can obtain better edge feature. Finally, Edge detection is applied to find crack in a bone of a hand. After experimentation, edge detection method proposed in this paper is Feasible.

Implementing Edge Detection for Medical Diagnosis of a Bone in Matlab

Background//Objectives: To analyze Brain MRI Images using Statistical techniques like Chi-square Automatic Interaction Detector (CHAID). The approach would help the researchers and doctors to automate the analysis of brain MRI images to classify the tumor from non tumor images to enhance the medical care. Method/Statistical Analysis: A novel approach is developed to detect grey matter so that tumor brain images can be classified from non tumor brain MRI images. Preprocessing of images, displaying of grey matter, segmentation, Grey matter extraction is done in Matlab environment. Classification of Brain MRI Images on the basis of Grey matter extracted is done using CHAID in XLSTAT tool. The novel approach uses the benefits of preprocessing methods and filters available in Matlab for effective extraction and analysis Brain MRI Images. Results/Findings: The work has been tested on 50 variables on seven patients. Out of seven three belong to healthy group and rest to unhealthy. The work is evaluated using classification tree, confusion matrix and ROC curve generated after CHAID analysis. The brain images are taken from the BRAINIX database. Conclusion/Application: It is easy to use the approach thereby providing an easy option to be used in hospitals and medical centers for the aid of the physicians.

Proposed Algorithm to Blotch Grey Matter from Tumored and Non Tumored Brain MRI Images

Background/Objectives: Study of biometric for human identification is trending nowadays. Several methods and algorithms have been suggested for the usage in biometric recognition system. â€œA biometric can be based on either a personâ€™s physical or behavioural characteristics.â€ The key approach behind the means is to uniquely recognize humans by their inherent physical characteristics. Recognition or identification through these biometric features dissipates the issues related with the traditional approaches for identifyinghumans. Humans are identified or recognized through their physical characteristics and not by any external entity that they must provide for the process. Methodology: The paper presents a short review of all the methods used for the biometric identification using lips by various people. The various papers have been read and studied. The algorithms were analyzed. Then the methods have been implemented to show the output. Results/Findings: Biometric identification such as lip prints is used to recognize every individual.Lip shape and features have been detected using various algorithms.

Review on Biometric Identification Using Lip Prints

/pdf/an-initiative-to-identify-depression-using-sentiment-54xrstewne.pdf

An initiative to identify depression using sentiment analysis: a machine learning approach

In applications of signal processing such as medicine, communications and satellites, preprocessing is considered as a vital step which focuses on reduction or removal of the level of the noise contained in the image. The process of denoising helps in preserving the finer details and useful information. Medical images like MRI, CT and X-ray contain very fine details that need to be correct and free from noise so that the information and features of interests are not lost during the diagnosis. In this paper, various noise reduction techniques such as wavelet transform, Neural Network, PCA, ICA and mean and median filters over medical images has been discussed. In this paper we tried to highlight the strength and weakness of various noise removal techniques over processing of the medical images.

Madhulika Bhatia

Papers

Implementing Edge Detection for Medical Diagnosis of a Bone in Matlab

Proposed Algorithm to Blotch Grey Matter from Tumored and Non Tumored Brain MRI Images

Review on Biometric Identification Using Lip Prints

An initiative to identify depression using sentiment analysis: a machine learning approach

An anatomization of noise removal techniques on medical images