http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Handwritten Indic Digit Recognition using Deep Hybrid Capsule Network
Mohammad Reduanul Haque,Rubaiya Hafiz,Mohammad Zahidul Islam,Mohammad Shorif Uddin International Journal of Computer ScienceNetwork S 2024 International journal of computer science and netw Vol.24 No.2
Indian subcontinent is a birthplace of multilingual people where documents such as job application form, passport, number plate identification, and so forth is composed of text contents written in different languages/scripts. These scripts may be in the form of different indic numerals in a single document page. Due to this reason, building a generic recognizer that is capable of recognizing handwritten indic digits written by diverse writers is needed. Also, a lot of work has been done for various non-Indic numerals particularly, in case of Roman, but, in case of Indic digits, the research is limited. Moreover, most of the research focuses with only on MNIST datasets or with only single datasets, either because of time restraints or because the model is tailored to a specific task. In this work, a hybrid model is proposed to recognize all available indic handwritten digit images using the existing benchmark datasets. The proposed method bridges the automatically learnt features of Capsule Network with hand crafted Bag of Feature (BoF) extraction method. Along the way, we analyze (1) the successes (2) explore whether this method will perform well on more difficult conditions i.e. noise, color, affine transformations, intra-class variation, natural scenes. Experimental results show that the hybrid method gives better accuracy in comparison with Capsule Network.
Mia Shamim,Ahmed Nasar Uddin,Islam Mohammad Zahidul,Rashad Md. Mainul Islam,Islam Md. Monirul,Zaman A. K. M. Mostafa 한국작물학회 2022 Journal of crop science and biotechnology Vol.25 No.2
Understanding genetic diversity of rice helps to improve its yield. Although many landraces of rice are grown in the coastal area of Bangladesh, their diversity has not been studied. Here, we report a comparison of 163 landraces of T. Aman rice. Data on diferent agronomic characters were collected while analysis of variance (ANOVA), Pearson’s regression, principal component analysis (PCA) and cluster analysis were performed. In addition, yield of local landraces was compared to modern cultivars using meta-analysis. Our results showed that the yield of local rice of this study was higher than both HYV and local rice grown in the farmers’ feld. Furthermore, landraces with longer plant height and heavier grain provided signifcantly higher yield. According to PCA, the highest contributing variables were the number of tillers per hill and plant height. Canonical variate analysis revealed that plant height and grain length–breadth ratio were major contributors in creating divergence. In the generalized distance (D2 ) and cluster analysis, landraces were split into fve diverse clusters with many sub-clusters. Considering overall diversity pattern, it is evident that a good number of T. Aman rice landraces can be used in future improvement programs for assembling many benefcial traits and increasing yield of rice.