KMITL

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

Browse

Settings

Author: search.filters.author.Pantuwong, NataponSubject: search.filters.subject.Feature point matching

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An Image-based Sea Turtle Identification using Postorbital Facial Feature Points Matching Technique
    (2019-10-01)
    Anuntachai, Anuntapat
    ;
    Pantuwong, Natapon
    Our natural environment and ecological system has recently become an alarming global concern due to the increase in worldwide pollution levels. Identifying individual wildlife is essential for understanding population and conservation planning. This paper takes this problem into account which focuses on the sea turtle. Traditionally, sea turtle individuals are identified through the application of external flipper tags or internal passive integrated transponders. However, such devices might be lost. This paper proposes a method to perform sea turtle identification using image recognition technique. This idea could be possible because each sea turtle has a unique postorbital facial pattern. To avoid light condition and color problem, we create a mesh of facial pattern, and use it as an image for matching process. The proposed method uses a modification of SIFT feature extraction technique to extract feature vector from the input facial image. The modification of SIFT is proposed to increase robustness against affine transform. The Euclidean distance with Optimize Random Sample Algorithm is used to calculate the matching score. According to the experimental result, the overall accuracy is 99.92%, which shows the good performance of our method.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A comparative study of feature point matching versus foreground detection for computer detection of dairy cows in video frames
    (2015-12-01)
    Pasupa, Kitsuchart
    ;
    Pantuwong, Natapon
    ;
    Nopparit, Suthasinee
    Behaviours of dairy cows reflect their health and emotions. Behavioural analysis by video surveillance is an accepted technique for helping cow-keepers to spot their cows' health problems. To perform a behavioural analysis, the presence and location of the cows need to be detected first. In this study, we used feature point matching method and foreground detection method to detect them. Two experiments were conducted in a dairy farm to detect cows in video frames recorded by a video camera installed over the top of a free-stall barn. A total of 800 frames of recorded cows' activities were captured. True and false positive and negative results were statistically confirmed by t test. We found that the accuracies of the feature point matching and foreground detection methods were 38.55 and 75.95 %, respectively; hence, for our setup, the foreground detection was a better method.