KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Access type: UnknownAuthor: search.filters.author.Tangsuksant, Watcharin

Search Results

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Comparison of Regression Algorithm for Vanishing Point Estimation based on Car Distribution
    (2019-11-01)
    Tangsuksant, Watcharin
    ;
    Noda, Masashi
    ;
    Kitagawa, Kodai
    ;
    Pintavirooj, Chuchart
    ;
    Wada, Chikamune
    In order to improve an application from the viewpoint of helping blind people waiting for the bus, classification of the vanishing view is required. The vanishing point from a perspective view is a feature that may improve the performance of viewpoint classification, especially in the case of congested traffic. The idea proposed by this study bases on the vanishing point estimation following car distribution on the road. In essence, the cars are detected using a You Only Look Once (YOLO) technique which extracts all the to the center point of a squared boundary. Normalization of the data points are then computed in percentages. Next is the calculation of the nineteen features of the data points of the car distribution. Finally, the vanishing point is estimated by supervised regression. This experiment compares the estimated results among five different regressions consisting of Linear, k-Nearest Neighbor, Decision Tree, Support Vector, and Multi-layer Per-ceptron regression. The obtain results show that the k-Nearest Neighbor regression computed the lowest distance error of 10.53, compared to the other regression algorithms.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Contactless palmprint alignment based on intrinsic local affine-invariant feature points
    (2014-02-12)
    Phromsuthirak, Choopol
    ;
    Tangsuksant, Watcharin
    ;
    Sanpanich, Arthorn
    ;
    Pintavirooj, Chuchart
    A Palmprint, biométrie characteristics, was mostly found in civil and commercial applications for security system because it has more reliable and easy to capture by low resolution devices. This paper was to develop a new contactless palmprint alignment with general USB camera on tripod. The palmprint image is acquired by this camera and using intrinsic local affine-invariant key points residing on the area patches spanning between two successive fingers to align palmprint image. The key points are relative affine invariant to affine transformations so this algorithm does not need the guidance pegs in acquisition process to fix hand position to avoid the scaling, translation and rotation problems for correctly palmprint image alignment. Finally, the developed algorithm was tested by 10 left-handed palmprint images collected from different subjects. The simulation results indicate by distance map error of 1.4899 pixels.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    American Sign Language recognition by using 3D geometric invariant feature and ANN classification
    (2014-01-20)
    Tangsuksant, Watcharin
    ;
    Adhan, Suchin
    ;
    Pintavirooj, Chuchart
    Communication between normal and disabled person has been developed in several researches. The hand gesture is one of important communication for the deaf, especially American Sign Language (ASL) which is used in order to represent each alphabet (A-Z). This paper aims to translate ASL from static postures. Besides, this research also designs the glove with six different colored markers and develops algorithm for alphabet classification. Moreover the system is set by two cameras in order to extract 3D coordinate points from each marker. There are three main important processes for algorithm consisting of marker detection by using Circle Hough Transform, computation of all feasible triangle area patches constructed from 3D coordinate triplet that is novel feature, and feature classification using feedforward backpropagation of Artificial Neural Network. The experimental result shows average of accuracy is 95 percent that is high performance and feasibility for proposed method.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Development algorithm to count blood cells in urine sediment using ANN and Hough Transform
    (2013-12-01)
    Tangsuksant, Watcharin
    ;
    Pintavirooj, Chuchart
    ;
    Taertulakarn, Somchart
    ;
    Daochai, Somsri
    Nowadays, microscopic is used in several laboratories for detect cells or parasite by technician. Especially testing in urine sediment is important for the patients who are abnormal about urinary tract. Constantly, the appearance of red blood cells, white blood cells, crystals, bacteria and other microorganisms in urine sediment's patients is more important information for diagnosis. This paper proposes the segmentation and detection of RBCs and WBCs in urine sediment images. The process of algorithm consists of three main parts. First step is segmentation by using feedforward backpropagation of Artificial Neural Network applied on the HSV color model image of urine sediment examination. The next step is eliminating noise by morphology operations. The last step is detection RBCs and WBCs by using Circle Hough Transform. Experimental results show the average percentage of error of RBCs and WBCs detection, 5.28 and 8.35 respectively. © 2013 IEEE.