Optical character recognition using KNN on custom image dataset

Hazra, Tapan Kumar; Singh, Dhirendra Pratap; Daga, Nikunj

doi:10.1109/iemecon.2017.8079572

Cited by 22 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of k > 1, a voting of majority decision is made to determine the class of the unknown sample. However, it can be seen from [5], [14], [17] that k = 1 consistently yields the highest accuracy and was verified by experimentation through the development process. Training the KNN classifier means saving the feature vectors from the training samples as opposed to other classifiers such as Support Vector Machines (SVM) and Artificial Neural Networks (ANN) in which parameters adapt or learn from the training samples.…”

Section: K-nearest Neighbor (Knn) As Character Classifiermentioning

confidence: 88%

Section: K-nearest Neighbor (Knn) As Character Classifiermentioning

confidence: 99%

“…KNN is an effective and widely used classifier in the industry despite is simplicity [4], [5]. It also has high fault tolerance over non-linear multiclass problems because it does not assume any models for the distribution of feature vectors in space [5], [8], [14]. KNN computes the distance from an unknown to all samples in the template space and remembers the minimum distance [5], [8], [14], [17].…”

Section: K-nearest Neighbor (Knn) As Character Classifiermentioning

confidence: 99%

“…It also has high fault tolerance over non-linear multiclass problems because it does not assume any models for the distribution of feature vectors in space [5], [8], [14]. KNN computes the distance from an unknown to all samples in the template space and remembers the minimum distance [5], [8], [14], [17]. The class that has the minimum distance from the unknown is the nearest neighbor k = 1 where the value k refers to the neighborhood size (Fig.…”

Section: K-nearest Neighbor (Knn) As Character Classifiermentioning

confidence: 99%

See 3 more Smart Citations

Development of License Plate Recognition on Complex Scene with Plate-Style Classification and Confidence Scoring Based on KNN

Montero

Jeong

2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

This paper presents an approach for developing an algorithm for automatic license plate recognition system (ALPR) on complex scenes. A plate-style classification method is also proposed in this paper to address the inherent challenges for ALPR in a system that uses multiple plate-styles (e.g., different fonts, multiple plate layout , variations in character sequences) which is the case in the current Philippine license plate system. Methods are proposed for each ALPR module: plate detection, character segmentation, and character recognition. K-nearest neighbor (KNN) is used as a classifier for character recognition together with a proposed confidence scoring to rate the decision made by the classifier. A small dataset of Philippine license plates but with relevant features of complex scenarios for ALPR is prepared. Using the proposed system on the prepared dataset, the performance of the system is evaluated on different categories of complex scenes. The proposed algorithm structure shows promising results and yielded an overall accuracy higher than the existing ALPR systems on the dataset consisting mostly of complex scenes.

show abstract

Section: K-nearest Neighbor (Knn) As Character Classifiermentioning

confidence: 88%

Section: K-nearest Neighbor (Knn) As Character Classifiermentioning

confidence: 99%

Section: K-nearest Neighbor (Knn) As Character Classifiermentioning

confidence: 99%

Section: K-nearest Neighbor (Knn) As Character Classifiermentioning

confidence: 99%

See 2 more Smart Citations

Development of License Plate Recognition on Complex Scene with Plate-Style Classification and Confidence Scoring Based on KNN

Montero

Jeong

2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…In training phase, KNN uses multidimensional feature vector space that assigns a class label to each training sample. Many researchers have suggested the use of KNN classifier in text/digits recognition and classification such as Hazra et al [22] who presented the concept of KNN classifier for both handwritten and printed letters recognition in English language based on sophisticated feature extractor technique.…”

Section: B K-nearest Neighbor (Knn)mentioning

confidence: 99%

KNN and ANN-based Recognition of Handwritten Pashto Letters using Zoning Features

Khan¹,

Ali²,

Ullah³

et al. 2018

ijacsa

View full text Add to dashboard Cite

This paper presents a recognition system for handwritten Pashto letters. However, handwritten character recognition is a challenging task. These letters not only differ in shape and style but also vary among individuals. The recognition becomes further daunting due to the lack of standard datasets for inscribed Pashto letters. In this work, we have designed a database of moderate size, which encompasses a total of 4488 images, stemming from 102 distinguishing samples for each of the 44 letters in Pashto. The recognition framework uses zoning feature extractor followed by K-Nearest Neighbour (KNN) and Neural Network (NN) classifiers for classifying individual letter. Based on the evaluation of the proposed system, an overall classification accuracy of approximately 70.05% is achieved by using KNN while 72% is achieved by using NN.

show abstract