Image analysis on color and texture for chili (Capsicum frutescence) seed germination

The objective of this research was to develop a computer system for evaluating the germination of a chili seed. The system called “chili seed germination analysis or (CSGA)”, evaluated the bird’s eye chili (Capsicum frutescence) seed and long fed pepper (Capsicum annuum var. acuminatum Fingerh.) seed germination by using an image processing technique. The chili seed images were taken by a mobile phone camera with 60 × microscope. The CSGA consisted of six main modules, namely 1) image acquisition, 2) seed image segmentation, 3) feature extraction, 4) germination evaluation, 5) result presentation and 6) germination verification. The CSGA employed color and texture features of chili-seed images to evaluate the germination. The system applied the Euclidean distance and a neural network technique to perform the system evaluation. The system precision rates were 59.71% and 71.71% for Euclidean distance and a neural network technique, respectively. The average access time was 0.74 seconds/image for the Euclidean distance and 3.54 seconds/image for the neural network technique.