Deep Learning Features Fusion with Classical Image Features for Image Access

Abstract

Depending on the society, the access to the adult content can create social problems. This paper thus proposes a fusion approach for image based adult content filtering. The proposed approach merges the Deep Learning (DL) architecture and classical hand crafted feature extraction approaches. From the DL, we fuse the rich feature extraction capabilities of the Convolutional Neural Networks (CNNs) with the Correlograms features. We optimize the classification by integrating and modifying the Correlograms into skin Correlograms. The results show an increased performance by combining the DL learnt features with the classical hand crafted features. From an evaluation, the proposed approach achieves an Accuracy of 0.93. This work thus motivates the usage of classical hand crafted features to be exploited in the DL architectures for segmentation and detection scenarios.

Authors and Affiliations

Rehan Ullah Khan

Keywords

Related Articles

Detection and Identification System of Bacteria and Bacterial Endotoxin Based on Raman Spectroscopy

Sepsis is a global health problem that causes risk of death. In the developing world, about 60 to 80 % of death cases are caused by Sepsis. Rapid methods for detecting its causes, represent one of the major factors that...

Secure Medical Internet of Things Framework based on Parkerian Hexad Model

Medical Internet of Things (MIoT) applications enhance medical services by collecting data using devices connected to the IoT. The collected data, which may include personal data and location, is transmitted to mobile de...

 Wavelet Time-frequency Analysis of Electro-encephalogram (EEG) Processing

 This paper proposes time-frequency analysis of EEG spectrum and wavelet analysis in EEG de-noising. In this paper, the basic idea is to use the characteristics of multi-scale multi-resolution, using four different...

Factors Associated to Online Shopping at the BoP Community in Rural Bangladesh

Online shopping is getting popular even in the rural areas of developing countries. However, few research has been conducted to identify the factors associated to online shopping by the poor villagers. Whereas people liv...

Plethora of Cyber Forensics

As threats against digital assets have risen and there is necessitate exposing and eliminating hidden risks and threats. The ability of exposing is called “cyber forensics.” Cyber Penetrators have adopted more sophistic...

Download PDF file
  • EP ID EP357405
  • DOI 10.14569/IJACSA.2018.090707
  • Views 103
  • Downloads 0

How To Cite

Rehan Ullah Khan (2018). Deep Learning Features Fusion with Classical Image Features for Image Access. International Journal of Advanced Computer Science & Applications, 9(7), 44-47. https://europub.co.uk/articles/-A-357405