Show simple item record

dc.contributor.authorRanjbarzadeh, Ramin
dc.contributor.authorJafarzadeh Ghoushchi, Saeid
dc.contributor.authorAnari, Shokofeh
dc.contributor.authorSafavi, Sadaf
dc.contributor.authorTataei Sarshar, Nazanin
dc.contributor.authorBabaee Tirkolaee, Erfan
dc.contributor.authorBendechache, Malika
dc.date.accessioned2022-12-02T07:34:06Z
dc.date.available2022-12-02T07:34:06Z
dc.date.issued2022en_US
dc.identifier.citationRanjbarzadeh, R., Jafarzadeh Ghoushchi, S., Anari, S., Safavi, S., Tataei Sarshar, N., Babaee Tirkolaee, E., & Bendechache, M. (2022). A Deep Learning Approach for Robust, Multi-oriented, and Curved Text Detection. Cognitive Computation, 1-13.en_US
dc.identifier.issn1866-9956
dc.identifier.issn1866-9964
dc.identifier.urihttp://dx.doi.org/10.1007/s12559-022-10072-w
dc.identifier.urihttps://hdl.handle.net/20.500.12713/3397
dc.description.abstractAutomatic text localization and segmentation in a normal environment with vertical or curved texts are core elements of numerous tasks comprising the identification of vehicles and self-driving cars, and preparing significant information from real scenes to visually impaired people. Nevertheless, texts in the real environment can be discovered with a high level of angles, profiles, dimensions, and colors which is an arduous process to detect. In this paper, a new framework based on a convolutional neural network (CNN) is introduced to obtain high efficiency in detecting text even in the presence of a complex background. Due to using a new inception layer and an improved ReLU layer, an excellent result is gained to detect text even in the presence of complex backgrounds. At first, four new m.ReLU layers are employed to explore low-level visual features. The new m.ReLU building block and inception layer are optimized to detect vital information maximally. The effect of stacking up inception layers (kernels with the dimension of 3 x 3 or bigger) is explored and it is demonstrated that this strategy is capable of obtaining mostly varying-sized texts further successfully than a linear chain of convolution layers (Conv layers). The suggested text detection algorithm is conducted in four well-known databases, namely ICDAR 2013, ICDAR 2015, ICDAR 2017, and ICDAR 2019. Text detection results on all mentioned databases with the highest recall of 94.2%, precision of 95.6%, and F-score of 94.8% illustrate that the developed strategy outperforms the state-of-the-art frameworks.en_US
dc.language.isoengen_US
dc.publisherSPRINGERen_US
dc.relation.isversionof10.1007/s12559-022-10072-wen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectDeep Learningen_US
dc.subjectText Detectionen_US
dc.subjectCurved Textsen_US
dc.subjectConvolutional Neural Networksen_US
dc.subjectText Segmentationen_US
dc.titleA deep learning approach for robust, multi-oriented, and curved text detectionen_US
dc.typearticleen_US
dc.contributor.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Endüstri Mühendisliği Bölümüen_US
dc.contributor.authorIDErfan Babaee Tirkolaee / 0000-0003-1664-9210en_US
dc.contributor.institutionauthorTirkolaee, Erfan Babaee
dc.relation.journalCOGNITIVE COMPUTATIONen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.contributor.wosauthoridErfan Babaee Tirkolaee / U-3676-2017en_US
dc.contributor.scopusauthoridErfan Babaee Tirkolaee / 57196032874en_US
dc.description.wosqualityQ2en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record