Intelligent Global Face Recognition

Khashman, Adnan

doi:10.5772/4838

Cited by 2 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of course, our natural recognition ability extends beyond face recognition, where we are equally able to quickly recognize patterns, sounds, and smells. Unfortunately, this natural ability does not exist in machines, thus the need for artificially simulating recognition in our attempts to create intelligent autonomous machines [25].…”

Section: Face Recognition Implementationmentioning

confidence: 99%

“…Previous works in [24,25] used successfully a conventional neural network based on the back propagation learning algorithm in addition to global pattern averaging for face recognition. Global pattern averaging is used for face image preprocessing prior to training or testing the neural network.…”

Section: Face Recognition Implementationmentioning

confidence: 99%

“…Additionally, this work provides a comparison between the performances of the emotional neural network and a conventional neural network based on the back propagation learning algorithm when implemented to a facial recognition problem. We use our face image database, which has been effectively used in our previous works [24,25]. The database comprises 270 images of 30 persons of various gender, ethnicity and age, with various lighting conditions and contrast.…”

Section: Introductionmentioning

confidence: 99%

“…Examples of the face image database[24,25]: faces with original contrast and different projections, looking right (LR), looking straight (LS), and looking left (LL) An example of the nine images for Person 14 resulting from three different face orientations (LS looking straight, LR looking right, LL looking left), and three different contrast levels (OC original contrast, LC low contrast, HC high contrast)…”

mentioning

confidence: 99%

See 3 more Smart Citations

Application of an emotional neural network to facial recognition

Khashman¹

2008

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

In our attempts to model human intelligence by mimicking the brain structure and function, we overlook an important aspect in human cognition, which is the emotional factor. It may currently sound unthinkable to have emotional machines; however, it is possible to simulate certain artificial emotions with the aim of improving machine learning. This paper investigates the efficiency of an emotional neural network, which uses a modified back propagation learning algorithm. The modifed algorithm, namely the emotional BP learning algorithm, has two emotional parameters, anxiety and confidence, that are modeled during machine learning and decision making. The emotional neural network will be implemented to a facial recognition problem using images of faces with different orientations and contrast levels, and its performance will be compared to that of a conventional neural network. Experimental results suggest that artificial emotions can be successfully modeled and efficiciently implemented to improve neural networks learning and generaliztion.

show abstract

Section: Face Recognition Implementationmentioning

confidence: 99%

Section: Face Recognition Implementationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations