BN-HTRd: A Benchmark Dataset for Document Level Offline Bangla Handwritten Text Recognition (HTR) and Line Segmentation

In this chapter, we introduce a new dataset for offline Handwritten Text Recognition (HTR) from images of Bangla scripts comprising words, lines, and document-level annotations. The BN- HTRd dataset is based on the BBC Bangla News corpus, meant to act as ground truth texts. These texts were subsequently used to generate the annotations that were filled out by people with their handwriting. Our dataset includes 788 images of handwritten pages produced by approximately 150 different writers. It can be adopted as a basis for various handwriting classification tasks such as end-to-end document recognition, word-spotting, word or line segmentation, and so on. We also propose a scheme to segment Bangla handwritten document images into corresponding lines in an unsupervised manner. Our line segmentation approach takes care of the variability involved in different writing styles, accurately segmenting complex handwritten text lines of curvilinear nature. Along with a bunch of pre-processing and morphological operations, both Hough line and circle transforms were employed to distinguish different linear components. In order to arrange those components into their corresponding lines, we followed an unsupervised clustering approach. The average success rate of our segmentation technique is 81.57% in terms of FM metrics with a mean Average Precision (mAP) of 0.547. This chapter introduces a new dataset for offline Handwritten Text Recognition from images of Bangla scripts comprising words, lines, and document-level annotations. The BN- HTRd dataset is based on the BBC Bangla News corpus, meant to act as ground truth texts. Data is the new oil in this era of the digital revolution. In order to make decisions through automatic and semi-automatic systems that employ machine learning and artificial intelligence, we need to convert the handwritten documents in government, and non-government organizations, such as those in banks or that involve legal decision making. Segmenting document images into their most fundamental parts, such as words and text lines, is regarded as the most challenging problem in the domain of handwritten document image recognition, where the scripts are curvilinear in nature. The task of handwriting recognition has captivated researchers for nearly a half-century.