Vision Language Models for Oil Palm Fresh Fruit Bunch Ripeness Classification

The accurate classification of fresh fruit bunch ripeness is crucial for optimizing oil quality and yield in the palm oil industry. Traditional manual inspection methods are labor-intensive, subjective, and prone to errors, motivating the exploration of automated solutions. This paper examined the potential of vision language models, including LLaVA 1.5, YiVL, and PaliGemma, to automate and enhance FFB ripeness assessment. The models were evaluated on their ability to classify ripeness stages and the accuracy of generated descriptive text using metrics like BLEU and ROUGE scores. Yi-VL achieved the highest descriptive accuracy with a ROUGE-L score of 93.14. However, it processes 0.18 samples per second, which is slower than PaliGemma (0.53 samples/second). PaliGemma is 194.44% more efficient in samples/second than Yi-VL, making it better suited for realtime applications despite its lower accuracy (ROUGE-L: 26.15). LLaVA 1.5 offers a balance between accuracy (ROUGE-L: 82.16) and efficiency (0.22 samples/second). This research highlighted the trade-offs between different VLMs for FFB ripeness assessment, demonstrating their potential to revolutionize the agriculture industry. Future work may focus on optimizing model performance and deploying these technologies in real-world scenarios.