As part of efforts to build a management system that can keep track of not only the food inside a refrigerator but also expiration dates, this paper introduces a smartphone application that can be used to recognize printed expiration dates. We began by investigating three open source optical character readers (OCRs) to determine the one most suitable to our needs, and then evaluated the selected OCR to determine how well it recognized expiration dates in numerous different environments. After encountering problems related to specific conditions, we designed and implemented an Android software application equipped with preprocessing functions to address them.

No abstract

In the present paper, we propose a deep network architecture in order to improve the accuracy of general object detection. The proposed method contains a proposal network and a classification network, which are trained separately. The proposal network is trained to extract a set of object candidates. These object candidates cover not only most object ground truths but also a number of false positives. In order to make the detector more robust, we train these object candidates using a secondary classifier. We propose combination methods and prove that a combination of two networks is more accurate than a single network. Moreover, we determine a new method by which to optimize the final combination results. We evaluate the proposed model using several object detection datasets (Caltech pedestrian, Pascal VOC, and COCO) and present results for comparison.

No abstract

Instance segmentation is a challenging task in computer vision because object locations in an image must be predicted and segmentation must be performed inside these locations. In the present paper, we propose a new pooling module to extract a small feature map from each Region of Interest for pixel-level prediction. Instead of using RoiAlign pooling, we use a small network module and ensemble the extracted multi-scale features in a feature map. The proposed method can output a better feature map and therefore better pixel-to-pixel alignment between input and output. The results of an experiment reveal that the proposed method outperforms cutting-edge instance segmentation methods.