R. C. Shivamurthy ¹, M. B. Manjunatha ²

Affiliations
1 Computer Science Engineering, Jain University, Bangalore - 560069, Karnataka, IN
2 Akshaya Institute of Technology, Tumkur - 572106, Karnataka, IN

Abstract

Image retrieval is like a system of in which, we can do searching and browsing then, finally retrieving a medical image from a very huge given a database of medical images. To identify or examine the image content, there must be some desired approaches. Hence, the goal of the proposed project is to retrieval of the histopathologicl image using CBIR method using GLCM technique. Finally, the results will be calculated by analyzing the results obtained in this method. Then we will calculate the GLCM contrast as well as GLCM correlation to retrieval of an image. These sets will enable new research opportunities, and they will improve and flow benchmark reviews. Our experimental result shows that our novel proposed method achieves better performance.

Keywords

GLCM Constrast, GLCM Correlation, Histopathological Image, Image Retrieval, Method, Medical Image

Full Text

   

B. P. Pradeep Kumar ¹, M. B. Manjunatha ²

Affiliations
1 Electronics Engineering, Jain University, Bangalore - 560069, Karnataka, IN
2 Akshaya Institute of Technology, Tumkur - 572106, Karnataka, IN

Abstract

Gesture based communication is a method of correspondence between the ordinary and hard of hearing people in which the vision based procedure is utilized. This paper proposes a novel methodology of hand gesture recognition system for American Sign Language (ASL), which will perceive communication via gestures signals in an ongoing situation. A hybrid based descriptor, which joins the benefits of LBP (Local binary pattern), SP (super pixels) and SURF (Speeded Up Robust Features) strategies, is utilized as a consolidated list of capabilities to accomplish a improved identification rate beside among a little moment in time computational difficulty. In additional increase the detection speed and create the appreciation framework strong to view-point varieties, the idea of derived features from the accessible list of capabilities is presented. K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) are utilized for hybrid arrangement of single marked letter. Comparative investigation of these strategies with other well known methods demonstrates that the constant proficiency and robustness are better. The performances parameters will be used in this method are accuracy, sensitivity, precision, FNR and FDR.

Keywords

American Sign Language, FNR, FDR, Hand Gesture Recognition, KNN, LBP, Recognition Rate, SP, SURF, SVM

Full Text

   

K. M. Shiva Prasad ¹, G. N. Kodanda Ramaiah ², M. B. Manjunatha ³

Affiliations
1 Electronics Engineering, Jain University, Bengaluru - 560069, Karnataka, IN
2 Department of ECE, K.E.C, Kuppam - 517425, Andhra Pradesh, IN
3 A.I.T., Tumkur - 572106, Karnataka, IN

Abstract

Speech synthesis is an artificial method of converting written text into machine generated speech. The Main Theme of this paper is to describe an overview of existing popular and advanced speech synthesizing techniques. Speech synthesis is a method of artificially generating the human speech from mathematical models and machines using some control parameters. The device which synthesizes is called as a synthesizer, the device which synthesizes is called as synthesizer and the synthesizer may be implemented as hardware or software. So for the research is not successful in generating a speech signal, usually researchers extract the speech parameters from the recorded speech and synthesize the original signal from it. A synthesizer can be viewed as Mathematical modeling of the vocal tract by extracting the acoustic/vocal features to produce the artificial generated speech output. The generated speech quality is described by its naturalness and intelligibility. The naturalness of synthesized speech gives an idea about how closely the generated output resembles the sounds produced by human speech production. Intelligibility describes how about the output can be understood by the listener after the perceiving it.

Keywords

HMM, Modelling, Speech Synthesis, TTS, Vocal Tract

Full Text

   

K. M. Shiva Prasad ¹, G. N. Kodanda Ramaiah ², M. B. Manjunatha ³

Affiliations
1 Electronics Engineering, Jain University, Bangalore – 560069, Karnataka,, IN
2 Department of ECE, KEC, Kuppam – 517425, Andhra Pradesh,, IN
3 A.I.T. Tumkuru – 572106, Karnataka,, IN

Abstract

Speech is the most natural and convenient way of human communication. The speech represents not only a sequence of steady states of some sounds which are abruptly changing from one to another or a sound signal which can be ignored after perceiving or hearing it. But human Speech is a unique signal which carries and conveys multiple levels of knowledge source, linguistic and non-linguistic information. Speech signals are the information bearing signals which are evolved as functions of a single independent variable like time. Speech is a complex acoustic wave resulted as output of speaker’s effort. Speech serves to communicate from speaker to one or more listeners. The typical sound is called phone and it is produced when a phoneme is articulated. Most of Indian languages have 20-50 phonemes which constitute an alphabet of sounds to describe the different words in that language. Generally the speech is composed of sentences made of words. Usually words are composed of phoneme sequences called syllables. Speech analysis plays a vital role in speech recognition and synthesis. Speech analysis is also known as feature extraction or as speech signal front ends.

Keywords

Feature Extraction, Front Ends, Human Communication, Speech

Full Text

   

R. C. Shivamurthy ¹, M. B. Manjunatha ²

Affiliations
1 Department of CSE, Jain University, Bangalore - 560069, Karnataka, IN
2 Department of ECE, AIT, Tumkur - 572106, Karnataka, IN

Abstract

Image feature extraction as well as retrieval of a medical image is a major problems CBIR technique. there is an improvement of networking and communication systems and other tools, which leads to imagine a numerous application for common users. The medical image retrieval is fast growing techniques in all the research fields. Many medical image retrieval approaches are still incapable to provide precise retrieval results along with high visual perception and also very less computational density. To report these issues, this paper illustrates and established a novel methodology for CBIR using 2D-Wavelet Transform (DWT). Here, we going to create a database of medical images utilizing CBIR method. DWT algorithm is applied to extract the feature of given query input image. By getting the horizontal and vertical projections of summation of pixels analyzing of BC coefficients are done. The Bhattacharyya Coefficients (BC) is used to find the similarity score of all the images. Based on the similarity score, the algorithm will select the most suitable images, similar to given query image. The highest value of BC images is the retrieved by the un trained database present in the system.

Keywords

Bhattacharyya Coefficients, CBIR Method, Chest X-ray Image, DWT, Healthcare Systems

Full Text

   

Anil Kumar Chandrashekar ¹, M. B. Manjunatha ²

Affiliations
1 Electronics Engineering, Jain University, Bangalore – 560069, Karnataka, IN
2 Akshaya Institute of Technology, Tumkur – 572106, Karnataka, IN

Abstract

The paper presents the notability of variation of vocal tract shape and formant frequency with its adjacent ratios, for the Indian English speakers for the five vowels of the English language. we have estimated the vocal tract shape of the Indian English speakers. For the estimation we have incorporated Autoregressive Model and the same for the formant frequency. The speech samples are considered with three various utterances namely the consumption of Ice cold water, with time relaxation of five minutes compared with normal recordings of the vowels namely /a/, /e/, /I/, /o/ and /u/. These utterances are recorded for 20 individual iterations. the vocal tract shape estimation and formant frequency estimation are done on the Matlab platform. the vocal tract shape of first vowel /a/ comes to normal shape rapidly with time lapse of five minutes. the vocal tract shape of vowel /e/ shrinks after consumption of ice cold water and slowly attains the normal shape. The vowel /I/ and /or/ vocal tract shape changes linearly for all the conditions considered, whereas the vocal tract shape of /u/ compresses for ice cold water and retains to be same even after a time lapse of five minutes. All the above variations are done by considering the vocal tract length of 17cm and it is modelled according to lossless uniform tube model. these outcomes are used for observation of vocal tract infection among the speech disorder patients, it can be adopted for the user authentication system by considering it as a vocal tract signature.

Keywords

English Vowels, Formant Frequency, Indian English, Vocal Tract Shape, Vowels.

Full Text