Anh Nam Le

Anh Le, Asanobu Kitamoto

Kindai documents, written in modern Japanese from the late 19th to early 20th century, hold significant historical value for researchers studying societal structures, daily life, and environmental conditions of that period. However, transcribing these documents remains a labor-intensive and time-consuming task, resulting in limited annotated data for training optical character recognition (OCR) systems. This research addresses this challenge of data scarcity by leveraging parallel textline images - pairs of original Kindai text and their counterparts in contemporary Japanese fonts - to augment training datasets. We introduce a distance-based objective function that minimizes the gap between self-attention features of the parallel image pairs. Specifically, we explore Euclidean distance and Maximum Mean Discrepancy (MMD) as domain adaptation metrics. Experimental results demonstrate that our method reduces the character error rate (CER) by 2.23% and 3.94% over a Transformer-based OCR baseline when using Euclidean distance and MMD, respectively. Furthermore, our approach improves the discriminative quality of self-attention representations, leading to more effective OCR performance for historical documents.

Quan Nguyen Minh, Bang Le Van, Can Nguyen et al.

People detection in top-view, fish-eye images is challenging as people in fish-eye images often appear in arbitrary directions and are distorted differently. Due to this unique radial geometry, axis-aligned people detectors often work poorly on fish-eye frames. Recent works account for this variability by modifying existing anchor-based detectors or relying on complex pre/post-processing. Anchor-based methods spread a set of pre-defined bounding boxes on the input image, most of which are invalid. In addition to being inefficient, this approach could lead to a significant imbalance between the positive and negative anchor boxes. In this work, we propose ARPD, a single-stage anchor-free fully convolutional network to detect arbitrarily rotated people in fish-eye images. Our network uses keypoint estimation to find the center point of each object and regress the object's other properties directly. To capture the various orientation of people in fish-eye cameras, in addition to the center and size, ARPD also predicts the angle of each bounding box. We also propose a periodic loss function that accounts for angle periodicity and relieves the difficulty of learning small-angle oscillations. Experimental results show that our method competes favorably with state-of-the-art algorithms while running significantly faster.