Injera is Ethiopian most common cultural food. This cultural food is prepared usually teff flour and sometimes prepared barley, corn, rice, sorghum, wheat, and a mixture of those flours. However, currently, a person mixes bad things with teff flour and other flour to make a high profit. A mixture of bad things with teff flour and other flour Injera has different problems like health problems for the user, loss of cultural identity, and marketing problems. Identification of Injera is difficult using naked eyes due to their visual similarities. Various researches have been done on food recognition and detection using different techniques. However, the previous researchers did not use image enhancement and color space conversion techniques. And also, the dataset used in different classes is less similar. In this study, we have performed Injera mixture identification using machine learning and computer vision approach. We prepared a combinational ratio of Injera datasets using traditional fermentation techniques. We captured hot Injera before 1 hour and cold Injera after 24 hours using Samsung Galaxy S5. In this study, we have used Grey Level Co-occurrence Matrix (GLCM), Convolutional Neural Network (CNN), and a combination of GLCM and CNN as a feature extraction and Support Vector Machine (SVM) and Random Forest (RF) as a classifier to design Injera mixture identification system. We have examined different combination ratios of hot and cold (after 24 hours) frontside and backside Injera. The proposed hybrid CNN and GLCM features trained with SVM and RF classifiers achieved the highest accuracy obtained in this work. From the experimental results, we registered an accuracy of 10:90 frontside hot Injera, 10:90 backside hot Injera, 10:90 frontside cold Injera, 10:90 backside cold Injera, 20:80 frontside hot Injera, 20:80 backside hot Injera, 20:80 frontside cold Injera, 20:80 backside cold Injera is 87%, 86%, 93%, 92%, 91%, 95%, 98%, and 98% for SVM and 88%, 87%, 91%, 91%, 93%, 94%, 98%, and 98% for RF respectively on combined features. Keywords: CNN, GLCM, Feature Extraction, SVM, Random Forest, Thresholding.