Montri Karnjanadecha

Montri Karnjanadecha
Prince of Songkla University · Department of Computer Engineering

About

39
Publications
20,118
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
190
Citations

Publications

Publications (39)
Article
Music selection is difficult without efficient organization based on metadata or tags, and one effective tag scheme is based on the emotion expressed by the music. However, manual annotation is labor intensive and unstable because the perception of music emotion varies from person to person. This paper presents an emotion classification system for...
Article
Biometric template protection approaches have been developed to secure the biometric templates against image reconstruction on the stored templates. Two cancellable fingerprint template protection approaches namely minutiae-based bit-string cancellable fingerprint template and modified minutiae-based bit-string cancellable fingerprint template, are...
Article
Color retinal images play an important role in supporting a medical diagnosis. However, some retinal images are unsuitable for diagnosis due to the non-uniform illumination. In order to solve this problem, we propose a method for improving non-uniform illumination that can enhance the image quality of a color fundus photograph suitable for reliable...
Conference Paper
Full-text available
Pedestrian detection is an increasingly interest research in computer vision with the challenging problem under complex background and occluded appearance in real world environment. The existing datasets have limitations for a large variation in human pose and clothing, variation of appearance, and cluttered backgrounds. In this paper, we considere...
Conference Paper
We are faced with a massive growth of musical data in the form of digital files. Accurate metadata labeling of music archives is necessary in order to make digital music searchable and to be efficiently organized, not only by file name or song title but in deeper detail, such as genre, artist, and types of instrument. Music related emotional terms...
Conference Paper
Contrast enhancement is a crucial method for improving the quality of an image. This paper proposes a visual contrast enhancement of a color imageby using histogram modification. Transfer function of the modified histogram was designed with generalized extreme value distribution. To automatically enhance image contrast and tone meanwhile improving...
Conference Paper
Full-text available
This paper presents the progress of the development of a Southern Thai dialect speech corpus to build automatic speech recognition. This is the recent Southern Thai dialect pronunciation dictionary containing more than 15,000 words, including words from a Southern Thai dialect dictionary, academic thesis papers, and online article resources. In thi...
Article
Studies of basic facial expression recognition have always shown different recognition rates for different emotional expressions. Happiness and surprise detection easily exceed 90% recognition rates, while other basic emotions (i.e. sadness, anger, fear, and disgust) produce much lower rates. In this paper we present a simple approach for reducing...
Article
A dual transmission model of the fetal heart sounds is presented in which the properties of the signals received on a sensor, installed on the maternal abdominal surface, depend upon the position of the fetus. For a fetus in the occiput anterior position, the predominant spectral content lies in the frequency band 16-50Hz ("impact" mode), but for a...
Article
Many speech segmentation techniques have been proposed to automate phonetic alignment. Most of the techniques require, however, labeled data to train, and perform well only for read, high-quality speech. Automatic phonetic alignment, for lower quality varied data with no labeled training data, the subject of this paper, is a much more challenging d...
Article
The fact that in Thai language emotions are not usually manifested, mostly because any emotion would interfere with meaning otherwise, makes this language very difficult for any kind of emotion recognition. Our proposed Thai emotion recognition system consists of two parts - speech emotion recognition and improvements of the system using face featu...
Article
In a study presented at the fall 2010 meeting of the Acoustical Society of America (Zahorian etal., "Time/frequency resolution of acoustic features for automatic speech recognition"), we demonstrated that spectral/temporal evolution features which emphasize temporal aspects of acoustic features, with relatively low spectral resolution, are effectiv...
Article
Nine hundred video clips (approximately 30 h in each of English, Mandarin, and Russian) have been collected from Internet sources such as youtube.com and rutube.ru. This multi-language audio/video database has been orthographically transcribed by human listeners with time markers at the sentence level. However, the aim is to provide this database t...
Conference Paper
Full-text available
Over the past few decades, research in automatic speech recognition and automatic speaker recognition has been greatly facilitated by the sharing of large annotated speech databases such as those distributed by the Linguistic Data Consortium (LDC). Open sources, particularly web sites such as YouTube, contain vast and varied speech recordings in a...
Article
Full-text available
A simple method for blood spatter analysis was implemented using an image processing technique. The advantagesof the computer application were exploited which subsequently provides minimal time consumed and user friendly interface.The outputs from the program associated with the string method are used for finding the origin of the incident, i.e. wh...
Article
Full-text available
Our multimodal biometric system combines fingerprinting with a top-view finger image captured by a CCD camera without user intervention. The greyscale image is preprocessed to enhance its edges, skin furrows, and the nail shape before being manipulated by a bank of oriented filters. A square tessellation is applied to the filtered image to create a...
Article
Full-text available
The identification of human basic actions plays an important role for recognizing human activities in complex scene. In this paper we propose an approach for automatic human action recognition. The parametric model of human is extracted from image sequences using motion/texture based human detection and tracking. Action features from its model are...
Article
This paper present the classification of fresh aromatic coconuts into 3 types: single layer, double layer and one and a half layer by inspecting colors at the bottom of coconuts. We take the photos the bottom of coconuts in RGB mode, change the colors into the HSV mode, and then place 4 circles into the image. The 20 photos of each type are used to...
Conference Paper
Full-text available
Hard disk's head (HDH) is one of the most important parts in a hard disk. Because the floating height between the HDH and the platter is very narrow, it is necessary to make sure that the HDH's pitch angle and roll angles are from -0.05° to 0.05° on the Head Stack Assembly (HSA). The maximum error is 0.0226° for pitch angle and 0.0288° for roll...
Conference Paper
Full-text available
This paper describes a motor control system for Robocup (small-size league) robot. Our aim was to build high performance robots at a minimal cost. We achieved a low-cost design with the use of cheap motors and use of small DC motors for speed feedback. All controls were completed by a single microcontroller. We also established predictive controlle...
Conference Paper
Full-text available
This paper describes an algorithm for automatic reference point detection in a top-view finger image recognition system. In tests of 700 finger images, only 6 images were rejected by our algorithm. A reference point location error correction technique was developed to improve the recognition accuracy. When using the proposed algorithm, the accuracy...
Conference Paper
Full-text available
This paper describes a feasibility study for using a top-view finger image to increase the accuracy of fingerprint recognition without adding any new user operations. A CCD camera captures a top-view finger image while the user is touching a fingerprint sensor, and the acquired gray scale image is preprocessed to enhance the edges, the skin furrows...
Article
Full-text available
This paper describes the pitch tracking techniques using autocorrelation method and AMDF (Average Magnitude Difference Function) method involving the preprocessing and the extraction of pitch pattern. It also presents the implementation and the basic experiments and discussions.
Article
Full-text available
This paper describes speech signal modeling techniques which are well-suited to high performance and robust isolated word recognition. We present new techniques for incorporating spectral/temporal information as a function of the temporal position within each word. In particular, spectral/temporal parameters are computed using both variable length...
Conference Paper
Full-text available
This paper presents an investigation of non-uniform time sampling methods for spectral/temporal feature extraction for use in automatic speech recognition. In most current methods for signal modeling of speech information, "dynamic" features are determined from frame-based parameters using a fixed time sampling, i.e., fixed block length and fixed b...
Conference Paper
Full-text available
Spectral feature computations continue to be a very difficult problem for accurate machine recognition of vowels especially in the presence of noise or for otherwise degraded acoustic signals. In this work, a new peak envelope method for vowel classification is developed, based on a missing frequency components model of speech recognition. Accordin...
Conference Paper
Full-text available
This paper presents speech signal modeling techniques which are well suited to high performance and robust isolated word recognition. Speech is encoded by a discrete cosine transform of its spectra, after several preprocessing steps. Temporal information is then also explicitly encoded into the feature set. We present a new technique for incorporat...
Conference Paper
Full-text available
Spectral/temporal segment features are adapted for isolated word recognition and tested with the entire English alphabet set using Hidden Markov Models. The ISOLET database from OGI and the HTK toolkit from Cambridge university were used to test our feature extraction technique. With our feature set we were able to achieve 97.3% recognition accurac...
Article
Full-text available
The objective of this paper is to propose a synthesis of some Thai monophthongs by basic articulatory synthesis. In this paper we first describe human speech production mechanism. After that we mention articulatory synthesis method. Our basic idea is to model the human articulators and vocal cords. The articulators are usually modeled with a set of...
Article
Full-text available
Progress on speech recognition of Thai digit strings is presented in this paper. HTK 3.0 was chosen to implement the HMM-based speech recognizer. MFCCs and their delta and delta-delta terms were used as speech features. Several set of HMM parameters were investigated. Two kinds of word searching methods were tried. Recognition accuracy of 98.7% on...
Article
Full-text available
This paper describes the design of a speech segmentation system for automatically transcribing speech utterances, which was developed as part of a speech corpus project. The system is HMM-based, with three states per model and three Gaussian mixtures per state. We explain how a short pause model was modified so that a transition from the entry stat...
Article
This paper describes the design and implementation of note recognition for Thai xylophones. Thai xylophone is a percussion musical instrument which can be played monophonically and polyphonically. A set of 21 digital bandpass filters are used to determines energy. An energy compensation technique is applied to normalize the loundness of the energy...
Article
Full-text available
Tone classification is a necessary part for Thai speech recognition. This paper present the work based on our former work described in our published paper ref. [1] and the published paper ref. [2]. Several configurations of tone classification front-end for large vocabulary Thai speech corpus are implemented and compared. They include the tone-crit...
Article
This paper describes the principle of MFCC feature extraction and the knowledge of human auditory masking effect in order to introduce a modified-MFCC feature extraction that can improve the robustness of speech recognition systems.

Network

Cited By

Projects

Project (1)
Project
Build Southern Thai Dialect Corpus, and Development Southern Thai Dialect Speech Recognition System