Offline Pashto Characters Dataset for OCR Systems

Abstract

In computer vision and artificial intelligence, text recognition and analysis based on images play a key role in the text retrieving process. Enabling a machine learning technique to recognize handwritten characters of a specific language requires a standard dataset. Acceptable handwritten character datasets are available in many languages including English, Arabic, and many more. However, the lack of datasets for handwritten Pashto characters hinders the application of a suitable machine learning algorithm for recognizing useful insights. In order to address this issue, this study presents the first handwritten Pashto characters image dataset (HPCID) for the scientific research work. This dataset consists of fourteen thousand, seven hundred, and eighty-four samples—336 samples for each of the 44 characters in the Pashto character dataset. Such samples of handwritten characters are collected on an A4-sized paper from different students of Pashto Department in University of Peshawar, Khyber Pakhtunkhwa, Pakistan. On total, 336 students and faculty members contributed in developing the proposed database accumulation phase. This dataset contains multisize, multifont, and multistyle characters and of varying structures.

Pashto Handwritten Invariant Character Trajectory Prediction Using a Customized Deep Learning Technique

“…Pashto, spoken in Afghanistan and parts of Pakistan (particularly the Khyber Pakhtunkhwa and Baluchistan provinces), is the language of the Pashtun ethnic group [1]. Pashto speakers are also known as Pakhtuns or Pashtuns [2]. It is the official language of Afghanistan and the second most widely spoken language in Pakistan.…”

“…Pashto literature covers various topics such as politics, religion, poetry, music, athletics, and education. However, the availability of modern technology and language services, including translation, text recognition, and speech recognition, is limited for Pashto speakers [2].…”

“…Pashto has a unique set of 44 characters [4,5], including other alphabets introduced by Pir Rokhan [4]. These characters combine to form different words, and their positioning in a word generates various ligature shapes [2]. Compared to other scripts like Arabic, Urdu, and Persian, Pashto exhibits a more significant variation in character shapes and a higher number of ligature joints.…”

“…Furthermore, different researchers created a Pashto single handwritten character dataset [1,2,12,13] with different implementation techniques and obtained different results. Researchers in [14] implemented HOG, which is helpful in various sorts of rotation because it is rotationally invariant.…”