The defect detection is an important activity in quality analysis and control in the fabric industry. The presented work gives a comparative analysis of artificial neural network and deep learning architectures. The MobileNet and deep residual network (ResNet) are deployed to classify the defective and nondefective fabric images. The hand-crafted morphological features are used in fabric image analysis along with feed backward selection feature reduction method to obtain the significant features. The overall classification rates of 95.3%, 98.2%, and 99.65% are obtained for Shallow, ResNet, and MobileNet architectures, respectively. The MobileNet model has given a maximum classification rate than Shallow and ResNet architectures. The work finds applications in apparel industry, quality analysis, cost estimation, online purchase of fabric, Industry 4.0, and so on.
The rate of growth of technology and the interactions of people made from far distance is at its maximum peak in the entire timeline of human history. These times therefore require an individual with accurate and legitimate updated knowledge of the incidents occurring to his immediate surroundings as well as of the entire globe. Owning devices such as smart phones, smart watches, tablets and other portable electronics of such kind is very common practice and the number of users is increasing day by day. NEWS was delivered through the means of messengers in medieval times, printing press in the 15th century. NEWS through television was convenient source of live information delivery which was popularized in 19th and 20th century. We have reached the epitome of fastest NEWS or information delivery system. This system however has a drawback in which the individual has to be in front of a television with a setup box and a bunch of wired cable which makes it a bit more tedious to get updated with information regularly. Hence, this can be improved by using the technology of applications on smart phones. The app will contain regular updates on topics which will be communicated by NEWS API. The API will get its information through various NEWS broadcasters available around the globe like BBC, CNN, Guardian, NDTV. This will greatly improve the speed of information reaching the average person. In comparison to the native apps, the average user of our app will be able to run it smoothly on their devices because of the minimalistic design while getting access to significant and latest NEWS. This feature not only drives the user to an information-centric source for day-to-day updates but can also keep the unwanted clutter away from the user experience. NEWS app allows us to explore the various types of integration available between foreign API’s and android application which transits to a unique experience for every user. It also provides us with an opportunity to learn the integration of the android application with Google's Firebase through which we would work and learn to manage and view the application’s analytics, explore push messaging services and much more features such as database management for android application.
Abstract:Image processing has a very big potential to do virtually anything. This project comes to the extent of development details on Recognition of osteoporosis through CT images. The objective of the recognition of osteoporosis is to identify and distinguish between a normal bone image and osteoporotic bone image with its case as severe or non-severe. Osteoporosis is due to the following two phenomena: a reduction in bone mass and a degradation of the micro architecture of bone tissue. Osteoporosis is a disease in which the quality of bone is reduced, leading to weakness of the skeleton and increased risk of fracture and change is observed in micro architecture. In this project we propose a methodology to build a system to identify the normal bone image and affected bone image with the case severe or non severe. We use contrast feature of the grey level co-occurrence matrix and apply thresholding to detect the normal or osteoporotic bone image.
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.