Chitsobhuk, Orachat

Preferred name

Chitsobhuk, Orachat

Main Affiliation

School of Engineering

orachat.ch@kmitl.ac.th

Now showing 1 - 10 of 42

Some of the metrics are blocked by your
consent settings
An improvement of PDLZW implementation with a modified WSC updating technique on FPGA
(2009-12-01)
Vichitkraivin, Perapong
;
Chitsobhuk, Orachat
In this paper, an improvement of PDLZW implementation with a new dictionary updating technique is proposed. A unique dictionary is partitioned into hierarchical variable word-width dictionaries. This allows us to search through dictionaries in parallel. Moreover, the barrel shifter is adopted for loading a new input string into the shift register in order to achieve a faster speed. However, the original PDLZW uses a simple FIFO update strategy, which is not efficient. Therefore, a new window based updating technique is implemented to better classify the difference in how often each particular address in the window is referred. The freezing policy is applied to the address most often referred, which would not be updated until all the other addresses in the window have the same priority. This guarantees that the more often referred addresses would not be updated until their time comes. This updating policy leads to an improvement on the compression efficiency of the proposed algorithm while still keep the architecture low complexity and easy to implement.
Some of the metrics are blocked by your
consent settings
Color descriptor for image retrieval in wavelet domain
(2006-01-01)
Utenpattanant, Ariya
;
Chitsobhuk, Orachat
;
Khawne, Amnach
This paper presents an approach to manage a large database using a compact color descriptor and a statistical method for accurately pruning the database. A compact color descriptor adopted in the proposed content-based image retrieval system is 63-bit binary Haar color histogram, which is very compact and can be effectively used for fast image search. In addition to fast searching using this compact descriptor, we further improve retrieval time by applying pruning technique, which looks for the candidate images similar to the query image from the database and ignore the rest that are not likely to the query image. The descriptors of the candidate images are then matched with that of the query. The most similar images will be retrieved and ordered according to their distance to the query. The proposed retrieval system can efficiently retrieve the most similar images from the database while can help reducing the retrieval time and the storage space.
Some of the metrics are blocked by your
consent settings
Image registration using hough transform, phase correlation and best-first search algorithm
(2007-12-01)
Chunhavittayatera, Siwaphon
;
Chitsobhuk, Orachat
This paper presents image registration using a combination of Hough transform, phase correlation and best-first search algorithm to estimate rotation and translation parameters. These parameters are used to register input images and create a seamless representation of the registered image. In the first step, the translation of angles are pre-calculated based on ID phase correlation in Hough space and used as candidate angles. Then, best-first search algorithm is applied to obtain the best translation of angle from candidate angles, which is used to de-rotated the input images. In the second step, the translation in x-y axis is computed using 2D phase correlation. Finally, the input images are registered using the estimated translation parameter. The experimental results using various image details and sizes show the accuracy of the proposed technique to detect the translation parameters. The best-first search algorithm can help to increase the precision of rotation parameter after Hough transform and phase correlation while require less amount of processing time compared to full search algorithm.
Some of the metrics are blocked by your
consent settings
Multi-pipeline architecture for face recognition on FPGA
(2009-11-18)
Visakhasart, Sathaporn
;
Chitsobhuk, Orachat
In this paper, a new multi-pipeline architecture is proposed for face recognition system on FPGA. The proposed structure consists of four main units: Multi-Pipeline Control Unit (MPCU), Process Element Unit (PEU), Region Summing Unit (RSU), and Recognition Indexing Unit (RIU). Four recognition techniques: Principal Component Analysis (PCA), Modular PCA (MPCA), Weight MPCA (WMPCA), and Wavelet based techniques are adopted to evaluate the efficiency of the proposed architecture using several standard face databases. The experimental results show that the proposed architecture helps minimizing processing time through its multi-pipeline processes while still maintains high recognition rate. Moreover, the design has encouraged the reduction in hardware resources by utilizing the proposed reusable modules. © 2009 IEEE.
Some of the metrics are blocked by your
consent settings
Image retrieval using connected color region and moment invariants
(2007-12-01)
Dongphontong, Daungkamol
;
Chitsobhuk, Orachat
In this paper, combined descriptors of Connected Color Region (CCR) and moment invariants are proposed as color features for a Content-Based Image Retrieval system. CCR provides the spatial information and maximum co-occurrence color while moment invariants help to better distinguish different distribution of colors in the image. From the experiments, the retrieval results using only CCR descriptors depend on CCR block size. The smaller the size of the block, the higher the retrieval performance. However, if the block size is small, it requires longer retrieval time. Therefore, in this paper, color moment is introduced as additional feature to CCR descriptors to help compromising between retrieval performance and time. The retrieval results using both CCR with large block size and moment descriptors are comparable to those of using only CCR with small block size while require less amount of retrieval time.
Some of the metrics are blocked by your
consent settings
Storm eye identification using fuzzy inference system
(2016-08-01)
Warunsin, Kulwarun
;
Chitsobhuk, Orachat
In this paper, a study of the novel technique based on Fuzzy Inference System (FIS) for storm eye identification has been presented. The ocean wind vectors are provided by the NASA QuikSCAT satellite to predict the significance of tropical cyclogenesis. This database is slightly noisy, incomplete and indirect. For this reason, the cloud satellite image can be an alternative option. However, the cloud shape may be ambiguous, which can introduce a long search time. As a result, utilizing combined information from both resources can lead to a reduction in resource deficiency. The FIS is used to describe the uncertain behavior of the complex system consisting of several factors. It provides ability to model the dynamic behavior of the storm and designates the best candidate eye position in the region of interest. Then, the spiral cloud model is adopted to enhance the search results in order to achieve the accurate eye position. The experimental results are conducted based on six reference storms. The proposed system offers higher flexibility in analyzing the storm eye position with the minimum average distance error of 92.8 km and approximately 16.25% less average distance error compared to the reference. This demonstrates the significant performance improvement in detecting the eye location of the storm.
Some of the metrics are blocked by your
consent settings
Variance training data in image enhancement
(2019-07-01)
Ngernplubpla, Jaturon
;
Chitsobhuk, Orachat
This paper presents a study of neuro-fuzzy behavior in clustering gradient profile spectral characteristics. Various types of image scene are chosen to evaluate neuro-fuzzy performance. The combinations of training data subsets are learned by ANFIS model to generate gradient profile priors, which are used as optimum weight selection criteria for image enhancement. The experimental results illustrate quantitative performance improvement and perceptual improvement in recovery of the high-resolution details in various images.
Some of the metrics are blocked by your
consent settings
Cross domain sentiment classification of Thai reviews using co-train model
(2019-01-01)
Boonpetch, Warakorn
;
Chitsobhuk, Orachat
Online reviews are significant sources of information, which is useful for supporting customer and entrepreneur decision in terms of product and service satisfaction analysis. Online reviews containing feedback from various domains makes it difficult to analyze and classify all comments at once. The proposed technique analyses the cross-domain Thai review data using a co-train machine learning model. The co-train model consists of multiple single domain specific models followed by refinement analysis for the final sentiment classification. This allows for full flexibility in training of each individual domain, which can lessen the limitation on training complexity due to simple training on single domain. The experiments have been conducted on Wongnai restaurant domain and IMDB movie domain data. Our co-train model can achieve the highest average accuracy of 86.10 percent for cross-domain sentiment classification with approximately 38 seconds processing time.
Some of the metrics are blocked by your
consent settings
Multidestination Indoor Navigation Using Path Planning and WiFi Fingerprint Localization
(2018-09-11)
Chitsobhuk, Orachat
;
Warunsin, Kulwarun
;
Udomthanapong, Sornchai
This paper presents an indoor navigation system based on multi-destination path planning and WiFi fingerprint localization. A user is allowed to specify multiple destinations and can detour the route at any time. Path planning will automatically update path using 2-opt and A∗ algorithms. The revised route will be analyzed according to user's current position supplied from the WiFi RSS fingerprint positioning. Naïve Bayes classification is adopted to learn from the RSS fingerprint priors stored in the database. Extensive experiments are conducted and performance comparison is analyzed and demonstrates significant performance improvement and higher noise tolerance with integration of the probabilistic priors. It can be seen that the proposed system enables user experience for indoor navigation service with support for automatic route updating and navigation refinement according to localization.
Some of the metrics are blocked by your
consent settings
A CNN-BASED MULTI-MODEL ENSEMBLE METHOD FOR INDOOR AND OUTDOOR MULTI-VIEW STEREO RECONSTRUCTION
(2022-01-01)
Wattanacheep, Bhattarabhorn
;
Chitsobhuk, Orachat
Camera poses estimation is a critical process that ensures the success of Three-Dimensional (3D) modelling. We present a Convolutional Neural Network (CNN)-based multi-model ensemble method for indoor and outdoor multi-view stereo reconstruction capable of learning across multiple domains, including images from both indoor and outdoor environments. Each domain’s images have distinct properties and shooting view-points, which leads to difficulty in efficient learning such a large difference and requires large amount of computational resources. In order to reduce complexity of the end-to-end single model, the proposed model is divided into multiple learning agents consisting of domain-specific agents and domain relationship agent. The domain-specific agent is trained independently on its own set of unique image characteristics, for example, one for indoor datasets and another for outdoor datasets. The domain relationship agent then ensembles and analyzes the multiple domain features and finalizes the estimation. In terms of average root mean square error, we compare the performance of the combined domain single model with the suggested ensemble CNN model. The experimental results indicate that the proposed model outperforms the others, with rotation and translation prediction errors of 0.112012266.

Chitsobhuk, Orachat

Filters

Settings

Sort By

Results per page