Sri Pujiyanto

Beef Quality Identification Using Thresholding Method and Decision Tree Classification Based on Android Smartphone

Beef is one of the animal food products that have high nutrition because it contains carbohydrates, proteins, fats, vitamins, and minerals. Therefore, the quality of beef should be maintained so that consumers get good beef quality. Determination of beef quality is commonly conducted visually by comparing the actual beef and reference pictures of each beef class. This process presents weaknesses, as it is subjective in nature and takes a considerable amount of time. Therefore, an automated system based on image processing that is capable of determining beef quality is required. This research aims to develop an image segmentation method by processing digital images. The system designed consists of image acquisition processes with varied distance, resolution, and angle. Image segmentation is done to separate the images of fat and meat using the Otsu thresholding method. Classification was carried out using the decision tree algorithm and the best accuracies were obtained at 90% for training and 84% for testing. Once developed, this system is then embedded into the android programming. Results show that the image processing technique is capable of proper marbling score identification.

Detection of the beef quality: Using mobile-based K-mean clustering method

Beef quality is determined by a number of parameters; some of which include size, texture, color feature, or meat smell. Recently, determining the meat quality is done by seeing the color and shape. However this method still has some weaknesses due to, for example, the subjectivity and inconsistency in human assessment. The aim of this research is to make an application to detect the meat quality. The application built was based on mobile using Java Programming Language on the Android integrated with Android SDK, Eclipse, and OpenCV. The method of image processing used pre-processing, k-mean clustering, and the analysis was conducted statistically with mean value and deviation standard. The quality detection meanwhile was performed using the texture and meat texture matching based upon the existing data. The application made could be used to seek the significant k-values and able to detect the level of quality by providing the level of accuracy at 80%.

Beef quality identification using color analysis and k-nearest neighbor classification

Beef is one of the many produce prone to contamination by microorganism. Water and nutrition contents make an ideal medium for the growth and proliferation of microorganism. Contaminated beef will degrade and has less storage duration. Beef is valued by two factors; its price and its quality. The quality itself is measured using four characteristics; marbling, color of meat, color of fat, and meat density. Specifically, marbling is the dominant parameter that determines meats quality. Determination of meat quality is conducted visually by comparing the actual meat and reference pictures of each meat class. This process is very subjective in nature. Therefore, this research aims to develop an automated system to determine meat by adopting the Indonesian National Standard requirement on the quality of carcass and beef (SNI 3932:2008) using the image processing technique. Image segmentation is carried out using the thresholding method and classification is conducted using the k-nearest neighbor algorithm. The features used to differentiate beef quality are marbling score, color of meat, and color of fat. Results indicate that the system developed is able to acquire images and identify beef quality as required in the Indonesian National Standard.