A Method of Effective Text Extraction for Complex Video Scene

Guo, Zhe; Yuan, Li; Wang, Yi; Liu, Shu; Tao, Linmi; Fan, Yangyu

doi:10.1155/2016/2187647

Cited by 6 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Shape-Based features analyzes the attributes at each pixel level, the shape-based features have properties of instinctiveness and optical in nature [30]. This research work is centering to compute the shape-based features such as Nodule Perimeter, Nodule Area, Nodule Irregularity Index, Convex Hull, Solidity, Equivalent Diameter [31].…”

Section: Shape-based Featuresmentioning

confidence: 99%

Lung Cancer Nodules Detection Using Ideal Features Extraction Technique in CT Images

Pawar,

Premchand,

Govardhanrao

2023

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

In the present time, worldwide the number of patients related to lung cancer disease getting increase exponentially, accordingly the application of Computer Aided Diagnosis (CAD) system building association with medical science to deliver pertinent solution using Image Processing and Machine Learning Techniques. This paper presenting a model for Lung Cancer nodules detection in CT image by employing proposed work in the progressive phases, the first step is image pre-processing which uses standard LIDC-IDRI images as input images, the preprocessing approach employ the denoising technique to remove the speckle noises from images, then by applying adaptive contrast enhancement (CLAhe) technique the quality of input CT image is improved. The second step works on to segment the Region of Interest (ROI) using LevelSet segmentation algorithm, the third step employed the learnable Feature Extraction technique from suspected (ROI) in CT image, the feature to be extracted from CT images are Texture Features such as Grey-Level Co-occurrence Matrix (GLCM), Grey-Level Run-Length Matrix (GLRM), Local Binary Pattern (LBP), Shape-Based Features such as Perimeter, Area, Irregularity Index, Solidity, Equivalent Diameter, Convex Area, and Statistical Features such as Mean, Median, Mode, Entropy, Moment, Skewness, and Kurtosis. The optimized measurable features are offered as input to the Hybrid-Layer Convolutional Neural Network, Hybrid-CNN applied Enhanced Cat-Swarm Optimization algorithm for optimal weight selection. The convolutional neural network trained based on feature values by varying the training percentage of dataset (in the range of 50%, 60%, 70%, 80%, and 90%) and the proposed model attains the elevated accuracy of 92.93%. The performance evaluation metrics are used such as Sensitivity, Specificity, Accuracy and F-Measure to evaluate the robustness of proposed Hybrid-CNN classification model.

show abstract

Section: Shape-based Featuresmentioning

confidence: 99%

Lung Cancer Nodules Detection Using Ideal Features Extraction Technique in CT Images

Pawar,

Premchand,

Govardhanrao

2023

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

show abstract

“…In this paper the extracted components of the shape features mainly include perimeter, area, volume, roundness, rectangularity, elongation, Euler number, Harris, Hu moment, ESV, SCDSTD, and ERCLD. Here some features are given [ 22 ]:…”

Section: Related Theorymentioning

confidence: 99%

Pulmonary Nodule Detection Model Based on SVM and CT Image Feature-Level Fusion with Rough Sets

Tao

Zhang

et al. 2016

BioMed Research International

View full text Add to dashboard Cite

In order to improve the detection accuracy of pulmonary nodules in CT image, considering two problems of pulmonary nodules detection model, including unreasonable feature structure and nontightness of feature representation, a pulmonary nodules detection algorithm is proposed based on SVM and CT image feature-level fusion with rough sets. Firstly, CT images of pulmonary nodule are analyzed, and 42-dimensional feature components are extracted, including six new 3-dimensional features proposed by this paper and others 2-dimensional and 3-dimensional features. Secondly, these features are reduced for five times with rough set based on feature-level fusion. Thirdly, a grid optimization model is used to optimize the kernel function of support vector machine (SVM), which is used as a classifier to identify pulmonary nodules. Finally, lung CT images of 70 patients with pulmonary nodules are collected as the original samples, which are used to verify the effectiveness and stability of the proposed model by four groups' comparative experiments. The experimental results show that the effectiveness and stability of the proposed model based on rough set feature-level fusion are improved in some degrees.

show abstract

“…3) script identification of the extracted titles. Understanding a language is believed to be much simpler than reading it because the latter requires deep knowledge of the script [2,3]. Quite often, audience with only speaking proficiency in a particular language face problems in reading and understanding the title in a movie poster written in that language.…”

Section: Introductionmentioning

confidence: 99%

Movie Title Extraction and Script Separation Using Shallow Convolution Neural Network

et al. 2021

View full text Add to dashboard Cite

Graphical texts in natural images play an important role in portraying information in multitudinous fields such as communication, education, and entertainment to name a few. Recognizing text in scene images is challenging due to the inherent complexity of the images. Text recognition in natural images involves script identification, which requires text localization. This is not trivial for natural scene images due to the presence of disparate foreground/background components. For scene images like movie posters, the challenge is more dominant. The challenges aggravate due to the presence of composite characteristics of posters like complex graphics background and the presence of different texts like a movie title, names of actors, producers, directors, and tagline. These texts have miscellaneous fonts, variations in colors, size, orientation, and textures. In this work, an M-EAST (modified EAST) model is proposed, which is based on the EAST (efficient and accurate scene text detector) model for text localization. A novel movie title extraction is thereafter used for separating the title from the extracted text pool. Finally, the title script was identified using a shallow convolutional neural network (SCNN)-based to ensure functionality in low-resource environments. Experiments were performed on a dataset of movieposter images of Tollywood, Bollywood, and Hollywood industries, and a highest accuracy of 99.82% was obtained. The system performed better than the reported techniques.

show abstract

A Method of Effective Text Extraction for Complex Video Scene

Cited by 6 publications

References 20 publications

Lung Cancer Nodules Detection Using Ideal Features Extraction Technique in CT Images

Lung Cancer Nodules Detection Using Ideal Features Extraction Technique in CT Images

Pulmonary Nodule Detection Model Based on SVM and CT Image Feature-Level Fusion with Rough Sets

Movie Title Extraction and Script Separation Using Shallow Convolution Neural Network

Contact Info

Product

Resources

About