KMITL

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

Browse

Settings

Author: search.filters.author.Titijaroonroj, TaravichetSubject: search.filters.subject.Convolutional neural network

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Seven Segment Display Detection and Recognition via Deep Learning Technique
    (2022-01-01)
    Suttapakti, Ungsumalee
    ;
    Titijaroonroj, Taravichet
    ;
    Nunsong, Walairach
    ;
    Kakanopas, Donyarut
    Seven segment display detection and recognition play an important role in determining the status of manufacturing machines. However, in some industrial factories, employees are still assigned to manually record the status of the seven segment displays. This is not real-Time tracking status and it is easy to make the typos or mistakes while collecting data. Hence, image processing and machine vision are used to automatically detect and recognize images from the seven segment displays. In this paper, the Cascade R-CNN is applied to automatically detect and recognize seven-segment displays in a single model-End-To-end learning because this method is efficient and flexible. The Cascade R-CNN method achieves precision, recall, and F1-score of 0.999 which are higher than conventional methods and the state-of-The-Art methods, including Faster R-CNN, RetinaNet, NAS-FPN, CornerNet, and CenterNet. Although the recognition accuracy of Cascade R-CNN is slightly lower than those of YOLOv3 and CornerNet, its accuracy is still higher than the Faster R-CNN, SSD, RetinaNet, NAS-FPN, and CenterNet. This method can automatically detect and recognize the digits on seven-segment display in a single model, thus improving the effectiveness for detecting and recognizing seven-segment display images.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Data augmentation based on multiscale radon transform for seven segment display recognition
    (2020-01-01)
    Popayorm, Sorawee
    ;
    Titijaroonroj, Taravichet
    ;
    Phoka, Thanathorn
    ;
    Massagram, Wansuree
    To alleviate the problem of limited data in creating rotation, scale, perspective, and illumination invariant of the neural network training sets, the multiscale Radon transform is proposed in this study to enhance the data augmentation for seven segment display recognition. Resizing, smoothing, and coefficient shifting generate the desired invariant effects for the training model. The accuracy rates from the experiment demonstrate the superiority of the proposed method over other data augmentation techniques with the best overall accuracy performance of 87.05%-outperforming other data augmentation techniques by 6-13%. The convolutional neural network model generated from the proposed multiscale Radon transform data augmentation is suitable for seven segment display recognition and could become beneficial to other type of self-luminous type of images.