The Reading-Life Log -- Technologies to Recognize Texts That We Read

Kimura, Takashi; Uchida, Seiichi; Omachi, Shinichiro; Kise, Koichi

doi:10.1109/icdar.2013.26

Cited by 9 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the classification of the reading and skimming scanpath has been studied in the past [1], these methods are not directly applicable here, because our objective is to identify a scanpath that belongs to a single line of text, with backward saccades allowed if they occur on the same line. In order to satisfy such a requirement, we implement a segment detection scheme based on the Kimura's return sweep detection algorithm [6]. Segments are detected when the size of the bounding box of consecutive translations is above a threshold.…”

Section: Segmentationmentioning

confidence: 99%

Vertical Error Correction Using Classification of Transitions between Sequential Reading Segments

Yamaya

Topić

Aizawa

2017

Journal of Information Processing

View full text Add to dashboard Cite

Abstract:In eye-tracking-based reading behavior research, gaze sampling errors often negatively affect gaze-to-word mapping. In this paper, we propose a method for more accurate mapping by first taking adjacent horizontally progressive fixations as segments, and then classifying the segments into six classes using a random forest classifier. The segments are then reconstructed based on the classification, and are associated with a document line using a dynamic programming algorithm. The combination of segment-to-line mapping and transition classification achieved 87% mapping accuracy. We also witnessed a reduction of manual annotation time when the mapping was used as an annotation guiding tool.

show abstract

Section: Segmentationmentioning

confidence: 99%

Vertical Error Correction Using Classification of Transitions between Sequential Reading Segments

Yamaya

Topić

Aizawa

2017

Journal of Information Processing

View full text Add to dashboard Cite

show abstract

“…In this paper, we focus on reading activity recognition. Reading is a pervasive and intellectual activity in daily life, and its recognition can be useful for building context-aware interfaces [12], life log systems [13,14] and experience sharing systems [15]. In addition, the image synthesis approach is useful for reading activity recognition, because one must take care of copyright issues when collecting the images of books and magazines for training.…”

Section: Introductionmentioning

confidence: 99%

First-person reading activity recognition by deep learning with synthetically generated images

Segawa¹,

Kawamoto

Okamoto

2018

J Image Video Proc.

View full text Add to dashboard Cite

We propose a vision-based method for recognizing first-person reading activity with deep learning. For the success of deep learning, it is well known that a large amount of training data plays a vital role. Unlike image classification, there are less publicly available datasets for reading activity recognition, and the collection of book images might cause copyright trouble. In this paper, we develop a synthetic approach for generating positive training images. Our approach synthesizes computer-generated images and real backround images. In experiments, we show that this synthesis is effective in combination with pre-trained deep convolutional neural networks and also our trained neural network outperforms other baselines.

show abstract

“…Vannevar Bush's memex (memory extender) was an optical device. Inspired by the progress of digital technology, contemporary researchers are reviving the notion of keeping track of what we read or see [2,3,4,5].…”

Section: Introductionmentioning

confidence: 99%

A Billion Words to Remember

Nagy¹

2017

View full text Add to dashboard Cite

Current wearable camera and computer technology opens the way for preservation of every printed, computer mediated and spoken word that an individual has ever seen or heard. Text images acquired autonomously at one frame per second by a 20 megapixel miniature camera and recorded speech, both with GPS tags, can be uploaded and stored permanently on available mobile or desktop devices. After culling redundant images and mosaicking fragments, the text can be transcribed, tagged, indexed and summarized. A combination of already developed methods of information retrieval, web science and cognitive computing will enable selective retrieval of the accumulated information. New issues are engendered by the potential advent of microcosms of personal information at a scale of about 1:1,000,000 of the World Wide Web.

show abstract

The Reading-Life Log -- Technologies to Recognize Texts That We Read

Cited by 9 publications

References 18 publications

Vertical Error Correction Using Classification of Transitions between Sequential Reading Segments

Vertical Error Correction Using Classification of Transitions between Sequential Reading Segments

First-person reading activity recognition by deep learning with synthetically generated images

A Billion Words to Remember

Contact Info

Product

Resources

About