A novel machine learning approach for scene text extraction

Ansari, Ghulam Jillani; Shah, Jamal Hussain; Yasmin, Mussarat; Sharif, Muhammad; Fernandes, Steven Lawrence

doi:10.1016/j.future.2018.04.074

Cited by 57 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A max-over-time pooling operation is made to obtain the maxc, and it is an essential feature [ 33 ]. A softmax, fully connected layer, is used to output the probability distribution of the labels.…”

Section: Deep Learning Methods For Ids Implementationmentioning

confidence: 99%

Sequential Model Based Intrusion Detection System for IoT Servers Using Deep Learning Methods

Zhong

Zhou

Chen

2021

Sensors

View full text Add to dashboard Cite

IoT plays an important role in daily life; commands and data transfer rapidly between the servers and objects to provide services. However, cyber threats have become a critical factor, especially for IoT servers. There should be a vigorous way to protect the network infrastructures from various attacks. IDS (Intrusion Detection System) is the invisible guardian for IoT servers. Many machine learning methods have been applied in IDS. However, there is a need to improve the IDS system for both accuracy and performance. Deep learning is a promising technique that has been used in many areas, including pattern recognition, natural language processing, etc. The deep learning reveals more potential than traditional machine learning methods. In this paper, sequential model is the key point, and new methods are proposed by the features of the model. The model can collect features from the network layer via tcpdump packets and application layer via system routines. Text-CNN and GRU methods are chosen because the can treat sequential data as a language model. The advantage compared with the traditional methods is that they can extract more features from the data and the experiments show that the deep learning methods have higher F1-score. We conclude that the sequential model-based intrusion detection system using deep learning method can contribute to the security of the IoT servers.

show abstract

Section: Deep Learning Methods For Ids Implementationmentioning

confidence: 99%

Sequential Model Based Intrusion Detection System for IoT Servers Using Deep Learning Methods

Zhong

Zhou

Chen

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…These selected features are then given to a SVM algorithm for verification, using an Artificial Neural Network (ANN) as a cost function. A few representatives classification methods [34][35][36][37][38][39][40][41][42][43][44][45][46][47] are also popular for scene character classification and further all these are useful for text/character recognition. Similarly, the other evolutionary algorithms including PSO and firefly are also considered as eminent tool among researchers for selecting best classification features.…”

Section: Related Workmentioning

confidence: 99%

“…The first step consists of resizing the input images into images to 100 100  pixels with the goal of maintaining the symmetry among all positive and negative text images. These samples are manually cropped using the benchmark datasets and illustrated in [40]. Next, we convert the color images into grayscale images.…”

Section: ) Preprocessingmentioning

confidence: 99%

An Optimized Feature Selection Technique in Diversified Natural Scene Text for Classification Using Genetic Algorithm

et al. 2021

Self Cite

View full text Add to dashboard Cite

Natural scene text classification is considered to be a challenging task because of diversified set of image contents, presence of degradations including noise, low contrast/resolution and the random appearance of foreground (font, style, sizes and orientations) and background properties. Above all, the high dimension of the input image's feature space is another major problem in such tasks. This work is aimed to tackle these problems and remove redundant and irrelevant features to improve the generalization properties of the classifier. In other words, the selection of a qualitative and discriminative set of features, aiming to reduce dimensionality that helps to achieve a successful pattern classification. In this work, we use a biologically inspired genetic algorithm because crossover employed in such algorithm significantly improve the quality of multimodal discriminative set of features and hence improve the classification accuracy for diversified natural scene text images. The Support Vector Machine (SVM) algorithm is used for classification and the average F-Score is used as fitness function and target condition. First after preprocessing input images, the whole feature space (population) is built using a multimodal feature representation technique. Second, a feature level fusion approach is used to combine the features. Third, to improve the average F-score of the classifier, we apply a meta-heuristic optimization technique using a GA for feature selection. The proposed algorithm is tested on five publically available datasets and the results are compared with various state-of-the-art methods. The obtained results proved that the proposed algorithm performs well while classifying textual and non-textual region with better accuracy than benchmark state-of-the-art algorithms.

show abstract

“…CNN performs promisingly in text and non-text discrimination problems [47] and also in text recognition [48,49]. Availability of task-specific huge dataset for training and high computing processing power is a major hurdle for deep neural networks.…”

Section: VIII Deep Neural Networkmentioning

confidence: 99%

Recent Advancements in Text Detection Methods from Natural Scene Images

Shiravale¹,

Sannakki²,

Rajpurohit³

2020

International Journal of Engineering Research and Technology

View full text Add to dashboard Cite

Effect of digitization and globalization has narrowed down the gap of geographical boundaries. Text/language plays an important role in getting connected with people utilizing oral or written communication. Nowadays text data is easily available in the form of multimedia e.g. audio, videos. A technique is needed to understand and interpret the text present in the videos/images which are rich in contents compared to audio data. Text detection and recognition are two main steps of such text-based applications. Text detection from natural scene images is tedious compared to text detection from document images. Various methods are available for text detection from natural scene images. Text detection methods are generally script specific. The main purpose of this paper is to highlight available text detection methods with pros and cons, challenges in the text detection process, evaluation parameters as well as recent achievements. The paper will act as a roadmap for upcoming researchers to select an appropriate text detection method.

show abstract

A novel machine learning approach for scene text extraction

Cited by 57 publications

References 20 publications

Sequential Model Based Intrusion Detection System for IoT Servers Using Deep Learning Methods

Sequential Model Based Intrusion Detection System for IoT Servers Using Deep Learning Methods

An Optimized Feature Selection Technique in Diversified Natural Scene Text for Classification Using Genetic Algorithm

Recent Advancements in Text Detection Methods from Natural Scene Images

Contact Info

Product

Resources

About