Volume 6 Issue 6
Design and Analysis of Fingerprint Rectification System using SVM Classifier
Author's Name: Raja Mohammed, Archana A S

Abstract—Elastic distortion of fingerprints is one of the major causes for false non-match. While this problem affects all fingerprint recognition applications, it is especially dangerous in negative recognition applications, such as watch list and de duplication applications. In such applications, malicious users may purposely distort their fingerprints to evade identification. In this project, we proposed novel method to detect and rectify skin distortion based on a single fingerprint image. Distortion detection is viewed as a two-class classification problem, for which the fingerprint feature vector is created and a SVM classifier is trained to perform the classification task. Here we use a database (called reference database) of various distorted reference fingerprints and corresponding distortion fields is built in the offline stage, and then in the online stage, the nearest neighbor of the input fingerprint is found in the reference database and the corresponding distortion field is used to transform the input fingerprint into a normal one. Promising results have been obtained on different latent Fingerprints.

Implemetation of Retinal blood vessels Detection System Using Deep Learning in poly clinic
Author's Name: Panchami R, Henry North

Abstract—Diabetic Retinopathy is one of the eye diseases which is caused due to retinal blood vessels extraction. Manual inspection of fundus images to check morphological changes in blood vessels and macula is a very time consuming and tedious work. It can be made easily with the help of computer aided system and inter variability for the observer. Here we proposed a system where we extract retinal blood vessels for detecting eye disease. Manually extracting the retinal blood vessels is long task there are many automated methods are available which makes work easier. The proposed system is used for classification of diabetic retinopathy leveraging with the help of deep learning. The approach classifies images based on characteristic features extracted by lesion detection and anatomical part recognition algorithms. User will input retina image into system. System will apply filtering techniques. Image pre-processing steps are applied to get accurate result. System will remove all unwanted objects from image. Finally system will detect diabetic retinopathy.

Malware Detection Approach in Android operating system using Hybrid Deep Learning Method
Author's Name: S Nair and Uma Shankari

Abstract— With the widespread use of smartphones, the number of malware has been increasing exponentially. Among smart devices, Android devices are the most targeted devices by malware because of their high popularity. This paper proposes a novel framework for Android malware detection. Our framework uses various kinds of features to reflect the properties of Android applications from various aspects, and the features are refined using our existence- based or similarity-based feature extraction method for effective feature representation on malware detection. Besides, a Hybrid deep learning method is proposed to be used as a malware detection model. This paper is the first study of the multimodal deep learning to be used in the Android malware detection. With our detection model, it was possible to maximize the benefits of encompassing multiple feature types. To evaluate the performance, we carried out various experiments with a total of 41,260 samples. We compared the accuracy of our model with that of other deep neural network models. Furthermore, we evaluated our framework in various aspects including the efficiency in model updates, the usefulness of diverse features, and our feature representation method. In addition, we compared the performance of our framework with those of other existing methods including deep learning based methods

Design and Study Analysis Automated Recognition system of Counterfeit Currency Notes
Author's Name: Krishna Veni SR, R.Anusuya

Abstract—Fake Currency has always been a drag which has created plenty of problems within the market. The increasing technological advancements have made the likelihood for creating more counterfeit currency which are circulated within the market which reduces the overall economy of the country. There are machines present at banks and other commercial areas to ascertain the authenticity of the currencies. But a typical man doesn't have access to such systems and hence a requirement for a software to detect fake currency arises, which can be used by folk. The proposed system uses Image Processing to detect whether the currency is genuine or counterfeit. The proposed system is implemented for a medical pharmacy shop. Therefore the proposed system contains 2 parts. The primary part may be a website for a pharmacy management which manages all the day-to-day operations of a medical pharmacy. The second part is that the fake currency recognition which identifies whether a not is genuine or not. This technique also can be implemented in malls, private financial institutions, supermarkets and also as an app or website that a standard man can recognize fake currency note. The Pharmacy Management System is developed with PHP as front and MySQL as rear. The fake currency recognition part is meant completely using Python programming language. It consists of the steps like grayscale conversion, edge detection, segmentation, etc. which are performed using suitable methods.

Implementation of Smart Diseases Prediction System Using Decision Tree Data Mining Algorithm
Author's Name: Ishank Darekar, Siddhi Desai, Prachi Govekar

Abstract— Medicines generates a strong deal of data stored in the medical database. Deriving useful knowledge and making scientific decision for diagnosis and treatment of disease from the database increasingly becomes important. Data mining in medicine can help to deal with this situation. It can also improve the management level of clinical information and endorse the development of community and telemedicine. The main objective of this system is to use the medicinal data and the algorithms are run on that information and result will be displayed in the form of user understandable words and graph. When very large data sets are present, data mining algorithms (here considering only ID3) is used. ID3 outputs the result in the form of decision tree which can be easily understood by end user. Recommender systems aim to provide users with personalized products and service to deal with the increasing online information overload problem.

Automated Smart Door Lock systme using IoT Technologies
Author's Name: Abhishekgowda K S , Nikhil U

Abstract— Security is major concern nowadays and today we have all types of surveillance and security system available in the market. But they are very expensive and sometimes create problems which we can’t solve. Security systems is one of the most researched fields of today. In this project an electronic device that can detect the human activity and switch on the doorbell automatically to notify the residents. The system will also be connected to the internet and can send the data to the cloud spontaneously. In this concept Arduino microcontroller act as the brain of the system. And the microcontroller will be connected with a Wi-Fi module to establish an internet connection. The smart device consists of radar motion sensors that detects the human activities over a particular range and can be placed in the door. The microcontroller will be program in such a way that whenever a human activity is detected by the radar motion sensors, the doorbell will switch on automatically and alert the residents regarding this. The system further to send a notification to a user and can also use a wireless camera to stream the video live online for security purposes and program the system to unlock the doors after receiving authentication from the user..