Brain Tumour Detection using Deep Learning Technique
AI Driven Detection and Remediation of Diabetic Foot Ulcer(DFU)
Advancements in Image Processing: Towards Near-Reversible Data Hiding and Enhanced Dehazing Using Deep Learning
State-of-the-Art Deep Learning Techniques for Object Identification in Practical Applications
Landslide Susceptibility Mapping through Weightages Derived from Statistical Information Value Model
An Efficient Foot Ulcer Determination System for Diabetic Patients
Statistical Wavelet based Adaptive Noise Filtering Technique for MRI Modality
Real Time Sign Language: A Review
Remote Sensing Schemes Mingled with Information and Communication Technologies (ICTS) for Flood Disaster Management
FPGA Implementation of Shearlet Transform Based Invisible Image Watermarking Algorithm
A Comprehensive Study on Different Pattern Recognition Techniques
User Authentication and Identification Using NeuralNetwork
Flexible Generalized Mixture Model Cluster Analysis withElliptically-Contoured Distributions
Efficient Detection of Suspected areas in Mammographic Breast Cancer Images
Face Recognition has benefitted greatly from the many databases that have been produced to study it. Most of these databases have been created under controlled conditions to facilitate the study of specific parameters on the Face Recognition problem. These parameters include such variables as Position, Pose, Lighting, Expression, Background, Camera Quality, Occlusion, Age, and Gender. While there are many applications for Face Recognition Technology in which one can control the parameters of Image Acquisition, there are also many applications in which the practitioner has little or no control over such parameters. This paper is provided as an aid in studying the latter, unconstrained, face recognition problem. The database represents an initial attempt to provide a set of labeled face photographs spanning the range of conditions typically encountered by people in their everyday lives. This paper describes a face detection system which goes beyond traditional face detection approaches normally designed for single faced images. The system described in this paper has been designed taking into account spatial coherence contained in multiple face detection. The resulting system builds a feature based model for each detected face, and searches them using various model information in the database. It provides a feasible way to locate the positions of two eyeballs, near and far corners of eyes, midpoint of nostrils and mouth corners from face image. This approach would help to extract useful features on human face automatically and improve the accuracy of face recognition.
The challenges in OCR system are many in the area of Handwritten Character and Word Recognition. From its very nature, Handwritten Character Word is a mixture of cursive and non-cursive segments. This leads to the problem of Recognition being significantly difficult. In this paper, the authors propose an intelligent system for recognition of handwritten Kannada words for recognition of the names of Districts and Taluks written on boards, land marks, etc. The proposed system applies an idea of subspace approach with popular Neural Network Architectures such as Generalized Regression Neural Network (GRNN) and Probabilistic Neural Network (PNN) for classification. This method is experimented on handwritten words comprising 189 (District & Taluk names of Karnataka State) classes.
In this paper, the authors tested the usefulness of most commonly used existing methods of writer recognition under different ink width conditions. A comparative study of Spatial Domain Features is presented in this paper. The existing methods give low error rate when they compare two handwritten images with different pen type. To improve the accuracy to a higher level histogram, variance in histogram bins and normalized histogram are used as features to recognize the handwriting. The system is tested for 981 writers with 2 samples, each with different writing instruments. The system is tested using Chain Code and Differential Chain Codes. Experimental result shows that the histogram of chain code outperform the other methods with 90.46 % as the recognition accuracy on this newly created dataset.
Automatic Language Identification is the task of identifying the Spoken Language, given utterance of speech. Many Communication Systems make use of this LID. Acoustic properties are used in many experiments, as it is easy to differentiate. Instead of using these features, prosodic properties can be used to identify the Language. The main idea is to explore the duration of neighboring syllable like units as a language discriminative feature. This paper proposes a LID which uses the rhythmic properties of Spoken Speech. Prosodic Features are extracted using Mel Frequency Cepstral Coefficients (MFCC). Based on the energy levels in the Signal, Phoneme Recognition is done to identify the syllable, like units. ANN is used to train the system and results are generated. The main focus of this paper is to improve the Recognition Accuracy. The error rate is reduced when compared with other systems.
Biometrics has an important role in privacy protection, when compared to traditional privacy protection methods like tokens, PIN, passwords etc. With the widespread use of fingerprint techniques in authentication systems, privacy protection of the fingerprint becomes an important issue. Traditional encryption is not sufficient for fingerprint privacy protection because decryption is required before the fingerprint matching, which exposes the fingerprint to the attacker. In recent years, significant efforts have been put into developing specific protection techniques for fingerprint. The main objective of this paper is to make a study on mixing fingerprints and how they are used in privacy protection of fingerprints. In this paper various methods of biometric template protection of fingerprint by mixing the fingerprints or multi-biometrics has been surveyed.
