Fast pornographic image recognition using compact holistic features and multi-layer neural network
| Autor: | I Gede Pasek Suta Wijaya, Ida Bagus Ketut Widiartha, Keiichi Uchimura, Muhamad Syamsu Iqbal, Ario Yudo Husodo |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: | |
| Zdroj: | IJAIN (International Journal of Advances in Intelligent Informatics), Vol 5, Iss 2, Pp 89-100 (2019) |
| Druh dokumentu: | article |
| ISSN: | 2442-6571 2548-3161 |
| DOI: | 10.26555/ijain.v5i2.268 |
| Popis: | The paper presents an alternative fast pornographic image recognition using compact holistic features and multi-layer neural network (MNN). The compact holistic features of pornographic images, which are invariant features against pose and scale, is extracted by shape and frequency analysis on pornographic images under skin region of interests (ROIs). The main objective of this work is to design pornographic recognition scheme which not only can improve performances of existing methods (i.e., methods based on skin probability, scale invariant feature transform, eigenporn, and Multilayer-Perceptron and Neuro-Fuzzy (MP-NF)) but also can works fast for recognition. The experimental outcome display that our proposed system can improve 0.3% of accuracy and reduce 6.60% the false negative rate (FNR) of the best existing method (skin probability and eigenporn on YCbCr, SEP), respectively. Additionally, our proposed method also provides almost similar robust performances to the MP-NF on large size dataset. However, our proposed method needs short recognition time by about 0.021 seconds per image for both tested datasets. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|