White-Box Evaluation of Computer Vision Algorithms through Explicit Decision-Making

Traditionally computer vision and pattern recognition algorithms are evaluated by measuring differences between final interpretations and ground truth. These black-box evaluations ignore intermediate results, making it difficult to use intermediate results in diagnosing errors and optimization. We propose “opening the box,” representing vision algorithms as sequences of decision points where recognition results are selected from a set of alternatives. For this purpose, we present a domain-specific language for pattern recognition tasks, the Recognition Strategy Language (RSL). At run-time, an RSL interpreter records a complete history of decisions made during recognition, as it applies them to a set of interpretations maintained for the algorithm. Decision histories provide a rich new source of information: recognition errors may be traced back to the specific decisions that caused them, and intermediate interpretations may be recovered and displayed. This additional information al...

• Type: Conference
• Year: 2009
• Where: ICVS
• Authors: Richard Zanibbi, Dorothea Blostein, James R. Cordy
• Keywords: Computer Vision, ICVS 2009, Pattern Recognition, Pattern Recognition Algorithms, Recognition Algorithms