Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Techno Nusa Mandiri : Journal of Computing and Information Technology

RECOGNITION OF REALTIME BASED PRIMITIVE GEOMETRY OBJECTS USING PERCEPTRON NETWORK Cut Lika Mestika Sandy; Taufik Ismail Simanjuntak; Ajulio Padly Sembiring; Reyhan Achmad Rizal; Ona Rizal Fahmi
Jurnal Techno Nusa Mandiri Vol 20 No 1 (2023): Techno Nusa Mandiri : Journal of Computing and Information Technology Period of
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v20i1.4104

Abstract

The purpose of this study is to analyze the perceptron model on pattern recognition of primitive geometric objects in real time based on video images. The samples used in this study were cubes, prisms, tubes and balls. The system was built using the Delphi 7 programming language with pre-processing stages system training includes the process of calculating matrix values from the original image, then proceed with the grayscale and edge detection processes using convolution with a kernel, namely the sobel operator and then the matrix results from the edge detection process are transformed using a perceptron network to obtain energy from the image of the object, then the resulting energy The transformation is stored in the database as a system test reference pattern recognition energy. Measurement of system performance evaluation in this study uses two parameters, namely detection rate and false positive rate. The recognition rate of primitive geometric objects using the perceptron network model in this study reaches 60.00% to 80.00%. The detection rate percentage shows that this model can be used as a supporting approach for the recognition of geometric objects in video.
REAL TIME DETECTION OF CHICKEN EGG QUANTITY USING GLCM AND SVM CLASSIFICATION METHOD Cut Lika Mestika Sandy; Asmaul Husna; Reyhan Achmad Rizal; Muhathir Muhathir
Jurnal Techno Nusa Mandiri Vol 20 No 2 (2023): Techno Nusa Mandiri : Journal of Computing and Information Technology Period of
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v20i2.4735

Abstract

A common problem currently being faced in the chicken egg production home industry is difficulty in counting the number of eggs. Currently, calculating the number of eggs is still done manually, which is less than optimal and prone to errors, so many entrepreneurs often experience losses. The manual system currently used also has the potential for this to happen. The use of technology on an MSME scale among laying hen breeders has not been widely adopted, this is due to limited access and understanding of technology. One alternative solution to deal with this problem is to build a real-time computerized system. The system that will currently be built in this research uses GLCM feature extraction and the SVM classification method. This system will detect egg production via CCTV cameras and will be stored in a database to be displayed on the website. The advantage of this system is that egg entrepreneurs can monitor chicken egg yields in real time. The results of trials that have been carried out using GLCM feature extraction and the SVM classification method in calculating the number of eggs using the SVM method with a polynomial kernel are highly recommended for use in this research because it can achieve 95% accuracy.