Recognition and verification of unconstrained handwritten words

Koerich, Alessandro L.; Sabourin, Robert; Suen, Ching Y.

doi:10.1109/tpami.2005.207

Cited by 62 publications

(40 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The criterion of a good ensemble system is that it should provide an increase in classification accuracy. There are numerous ways of combining classifiers as suggested by previous studies [19] with a wide variety of applications contributed from text categorization [20] and hand-written word recognition [21]. In particular, a few examples of related studies in remote sensing include [17,[22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Maximizing the Diversity of Ensemble Random Forests for Tree Genera Classification Using High Density LiDAR Data

Sohn

Remmel

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

Recent research into improving the effectiveness of forest inventory management using airborne LiDAR data has focused on developing advanced theories in data analytics. Furthermore, supervised learning as a predictive model for classifying tree genera (and species, where possible) has been gaining popularity in order to minimize this labor-intensive task. However, bottlenecks remain that hinder the immediate adoption of supervised learning methods. With supervised classification, training samples are required for learning the parameters that govern the performance of a classifier, yet the selection of training data is often subjective and the quality of such samples is critically important. For LiDAR scanning in forest environments, the quantification of data quality is somewhat abstract, normally referring to some metric related to the completeness of individual tree crowns; however, this is not an issue that has received much attention in the literature. Intuitively the choice of training samples having varying quality will affect classification accuracy. In this paper a Diversity Index (DI) is proposed that characterizes the diversity of data quality (Q i ) among selected training samples required for constructing a classification model of tree genera. The training sample is diversified in terms of data quality as opposed to the number of samples per class. The diversified training sample allows the classifier to better learn the positive and negative instances and; therefore; has a higher classification accuracy in discriminating the "unknown" class samples from the "known" samples. Our algorithm is implemented within the Random Forests base classifiers with six derived geometric features from LiDAR data. The training sample contains three tree genera (pine; poplar; and maple) and the validation samples contains four labels (pine; poplar; maple; and "unknown"). Classification accuracy improved from 72.8%; when training samples were selected randomly (with stratified sample size); to 93.8%; when samples were selected with additional criteria; and from 88.4% to 93.8% when an ensemble method was used.

show abstract

Section: Introductionmentioning

confidence: 99%

Maximizing the Diversity of Ensemble Random Forests for Tree Genera Classification Using High Density LiDAR Data

Sohn

Remmel

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In fact, several recognition systems in the literature are based on Hidden Markov Models [20], [37]. Lee and all [21] have developed a new hybrid approach to the verification of handwritten addresses in Singapore.…”

Section: State Of the Art And Problematicmentioning

confidence: 99%

A New Approach for Arabic Handwritten Postal Addresses Recognition

Charfi¹,

Kherallah²,

Baati³

et al. 2012

IJACSA

View full text Add to dashboard Cite

Abstract-In this paper, we propose an automatic analysis system for the Arabic handwriting postal addresses recognition, by using the beta elliptical model. Our system is divided into different steps: analysis, pre-processing and classification. The first operation is the filtering of image. In the second, we remove the border print, stamps and graphics. After locating the address on the envelope, the address segmentation allows the extraction of postal code and city name separately. The pre-processing system and the modeling approach are based on two basic steps. The first step is the extraction of the temporal order in the image of the handwritten trajectory. The second step is based on the use of Beta-Elliptical model for the representation of handwritten script. The recognition system is based on Graph-matching algorithm. Our modeling and recognition approaches were validated by using the postal code and city names extracted from the Tunisian postal envelopes data. The recognition rate obtained is about 98%.

show abstract

“…5), two groups will be created: (2,3,3), (2,4,3), (3,4,4), (3, 5, 4)} and G 2 = {(5, 7, 6), (5,8,7), (6,7,6), (6,8,6), (6, 8, Step 4: Create correctly segmented regions from each group. At this step we process every group G i , i = 1, ... , l independently.…”

Section: R N )] }mentioning

confidence: 99%

“…Combining classifiers is a well researched topic in the pattern recognition community [1], for example in word recognition [2], spoken language processing [3] and biometric applications [4]. In classifier combination, rules are used to combine the outputs of multiple classifiers.…”

Section: Introductionmentioning

confidence: 99%