Conversational Image Recognition Chatbot Using Computer Vision and Natural Language Processing

Abstract: Conversational image recognition combines image understanding with natural language interaction so that a user can upload an image and ask questions about its content. This research proposes a practical framework for a conversational image recognition chatbot using Computer Vision and Natural Language Processing (NLP). The proposed approach accepts an image and a natural-language query, processes visual and textual information, combines the resulting representations, and generates a conversational response. Visual recognition can use Convolutional Neural Networks or Vision Transformers for extracting image features, while language processing handles the user question and conversation context. Vision-language models such as CLIP, BLIP, BLIP-2, and LLaVA provide useful directions for connecting visual and textual information. The chatbot can support image description, object-related questions, simple visual question answering, and follow-up questions. Evaluation will consider recognition quality, answer relevance, response consistency, error cases, and processing time. The study is designed as a practical research framework in which the final performance values will be obtained after implementation and testing.

Keywords: Conversational AI, Image Recognition, Computer Vision, Natural Language Processing (NLP), Visual Question Answering, Image Captioning, Vision-Language Models, Multimodal Chatbot.