This paper introduces a novel deep learning architecture, named DIGITNET, and a large-
scale digit dataset, named DIDA, to detect and recognize handwritten digits in historical …

This paper presents a systematic literature review of image datasets for document image
analysis, focusing on historical documents, such as handwritten manuscripts and early …

Handwritten digit recognition is an active research field. These recognition systems are
faced with many challenges, including accuracy, speed and automatic extraction of complex …

The overlapped handwritten digit classification is a global challenge and a significant
measure to assess the network recognition ability ratio. Most efficient models have been …

Abstract Artificial Immune Recognition System (AIRS) offers a promising meta-heuristic
approach inspired by the human immune system for classification tasks. However …

Predstavljen je sistem za umetno prepoznavanje imunosti (O-AIRS) izboljšuje natančnost
klasifikacije z uporabo homogenih antigenskih skupin (HAG) in mehanizma zrelosti za …

The most common application of artificial immune networks (AINs) is on unsupervised
learning tasks. This is due to the fact that AINs are inspired by the adaptive immune system …

Handwriting recognition is the automatic transcription of handwriting, where only the image
of the handwriting is available. Manual matching shall be used by banks for the …

Handwriting recognition is the automatic transcription of handwriting, where only the image
of the handwriting is available. Manual matching shall be used by banks for the …

One of the most important challenges in pattern recognition applications is the recognition of
handwritten characters. This thesis presents the steps of building a Machine Learning model …