Sketch-based manga retrieval using manga109 dataset

Abstract

Manga (Japanese comics) are popular worldwide. However, current e-manga archives offer very limited search support, including keyword-based search by title or author, or tag-based categorization. To make the manga search experience more intuitive, efficient, and enjoyable, we propose a contentbased manga retrieval system. First, we propose a manga-specific image-describing framework. It consists of efficient margin labeling, edge orientation histogram feature description, and approximate nearest-neighbor search using product quantization. Second, we propose a sketch-based interface as a natural way to interact with manga content. The interface provides sketchbased querying, relevance feedback, and query retouch. For evaluation, we built a novel dataset of manga images, Manga109, which consists of 109 comic books of 21,142 pages drawn by professional manga artists. To the best of our knowledge, Manga109 is currently the biggest dataset of manga images available for research. We conducted a comparative study, a localization evaluation, and a large-scale qualitative study. From the experiments, we verified that: (1) the retrieval accuracy of the proposed method is higher than those of previous methods;(2) the proposed method can localize an object instance with reasonable runtime and accuracy; and (3) sketch querying is useful for manga search.

Adaptive Densely Connected Single Image Super-Resolution

“…In order to verify the validity of the model , we compare the performance on five standard benchmark datasets: Set5 [1], Set14 [27], B100 [17], Urban100 [8], and manga109 [18]. In terms of PSNR, SSIM and visual effects, We compare our models with the state-of-theart methods including Bicubic, SRCNN [5], VDSR [10], LapSRN [12], MemNet [22], EDSR [16], RDN [32], RCAN [31], SAN [4].…”

Digital Comics Image Indexing Based on Deep Learning

“…Some other works focus on character retrieval [53][54][55]. The work in [53] shows good results for character retrieval using local feature extraction and the approximate nearest neighbors (ANN) search.…”

“…In [54], authors used Frequent Subgraph Mining (FSM) techniques for comic image browsing using query-by-example (QBE) model. In [55], authors proposed a manga-specific image-describing framework. It consists of efficient margin labeling, edge orientation histogram, feature description, and approximate nearest-neighbor search using product quantization.…”

“…This field of research includes content segmentation [5], relation analysis [6], style analysis [7] and information retrieval [8]. While information retrieval research domain has a long history, content-based comics indexing and the creation of comics in a digital form are quite recent.…”

Analysis of Evolutionary Behavior in Self-Learning Media Search Engines

“…With the explosive growth of multimedia information in contemporary social networks, effective retrieval of a wide variety of digital media has drawn increasing attention in both business and research realms [1], [2]. Current prevailing search methods, such as PageRank, tf-idf, and BGSA [3], has achieved impressive performance in classic text retrieval [4], [5].…”