What Do We Do

This Computational Analytics & Cognitive Vision (CACV) Lab tends to discover various types of feature extractors that can effectively describe the local textural or motion features of objects. For example, the detection and recognition of facial micro-expressions to reveal the concealed feelings of a person, the design of automatic defect detection of leather surfaces to facilitate the manufacturing process in the factory, and physical geometry estimation of food material. Several experiments were carried out in the lab and thorough analysis was provided for each proposed method to highlight the contributions made and limitations encountered.

計算分析與認知視覺實驗室試圖探討各種類型的特徵提取算法以有效地描述物體的紋理、形狀、空間關係的特徵。例如，通過面部微表情的檢測與識別來揭示個人隱藏的情感，自動檢測皮革表面缺陷以簡化部分工廠的製造過程及食品材料的物理幾何估算。我們在實驗室中進行了這些實驗，並對提出的每個方法進行了全面的分析，描述了算法的特色、作出的貢獻與其優缺點。