Browsing by Author "Marcos, Nelson"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Automatic mango detection using Image processing and HOG-SVM
    (Association for Computing Machinery, 2018-12) Baculo, Maria Jeseca C.; Marcos, Nelson
    Mango is an agricultural produce with high export value as it is being consumed internationally. To ensure its production yield, the manual handling and classification tasks should be performed with precision and care by local farmers. Image processing and machine learning has improved the way classification, defect detection, and yield approximation are handled. Detection is considered as an initial step prior to performing these tasks. This paper presents an automatic mango detector by combining a Support Vector Machine (SVM) classifier trained with Histogram of Oriented Gradients (HOG) features and image segmentation. The image segmentation performed on both HSV and RGB color spaces using image processing techniques achieved a mean IoU of 0.7938. A HOG-SVM based classifier was trained and achieved an F-score of 89.38%. Results show that combining segmentation with HOG-SVM can detect and localize healthy and defective mango images with different background color and illumination.
  • Thumbnail Image
    Item
    Towards tobacco leaf detection using Haar cascade classifier and image processing techniques
    (Association for Computing Machinery, 2018-10) Marzan, Charlie S.; Marcos, Nelson
    Tobacco grading needs an effective leaf detection algorithm to ensure accurate results in segmentation and feature extraction. Leaf detection in this research used Haar cascade classifier and image processing techniques to automatically detect tobacco leaves in images. The proposed detection algorithm was implemented through OpenCV Python. The Haar cascade classifier was trained with 1,000 images and tested with 150 images. To improve the detection results of the classifier and ultimately detecting tobacco leaves, image processing techniques such as converting RGB to grayscale, blurring, thresholding, and finding connected components were applied. The experimental results show that the classifier can successfully distinguish tobacco leaves from other objects even those having resemblance to the characteristics of tobacco leaves in terms of color and shape. The accuracy rate of at least 91.33% proves the capability of the Haar cascade classifier to detect single and multiple tobacco leaves posed at different angles and taken at different distances from the camera. After applying some image processing techniques, the detection rate reached 100.00% and took 62 ms on average.