Özet:

Appearance is an important factor in the quality classification of products in fruit and vegetable markets. Existing manual methods are used to check the disease, pesticide and quality status of crops during the control stages of agricultural production. Manual sorting and grading of products may require expertise, which is time-consuming and labor-intensive. Today, with the advancement of technology, software techniques used in agriculture and food are also developing. The use of software techniques in the processing and marketing of agricultural and food products is becoming widespread. With the study to be carried out, date palm fruit, which has an important share in the fruit and vegetable market, will be discussed. Using image processing and artificial intelligence techniques to classify the quality of date fruits can make the sales process more consistent and time efficient. Within the scope of the study, various artificial intelligence techniques were used with a uniquely prepared dataset. The dataset consists of 3 different classes. These include images of good, bad and medium quality date fruits. MobileNetV2, ResNet50V2, DenseNet201 and InceptionV3 models were trained with the original dataset. In addition, the software techniques to be used in this field can be integrated with automation systems in the future stages of the study. An automation system using artificial intelligence and image processing techniques can autonomously distinguish fruits according to their quality. This will be emphasized in the later stages of the study.

Anahtar Kelimeler: