A neural 3-D object recognition architecture using optimized Gabor filters
نویسندگان
چکیده
We present an object recognition architecture based on feature extraction by Gabor filter kernels and feature classification by an artificial neural network. The parameters of the Gabor filters are optimized to the specific problem by minimizing an energy function. Such Gabor filters extract features that can be more easily classified by the neural network. Moreover the feature space is low-dimensional, so feature extraction doesn' t require much computational effort. The object recognition system is implemented on a Datacube and works in real-time.
منابع مشابه
Fast Gabor Filters for Object Recognition of Mobile Robot
Gabor filters have been used extensively in areas related to feature extraction of images due to their localization in space and bandlimited properties. Since 2-D Gabor filters have more complexity of computation, they have been used in static image decompositions rather than for mobile robots. In an attempt to reduce complexity of computation of 2-D Gabor filters for mobile robots, in this pap...
متن کاملOn the use of Textural Features and Neural Networks for Leaf Recognition
for recognizing various types of plants, so automatic image recognition algorithms can extract to classify plant species and apply these features. Fast and accurate recognition of plants can have a significant impact on biodiversity management and increasing the effectiveness of the studies in this regard. These automatic methods have involved the development of recognition techniques and digi...
متن کاملMultiple local feature representations and their fusion based on an SVR model for iris recognition using optimized Gabor filters
Gabor descriptors have been widely used in iris texture representations. However, fixed basic Gabor functions cannot match the changing nature of diverse iris datasets. Furthermore, a single form of iris feature cannot overcome difficulties in iris recognition, such as illumination variations, environmental conditions, and device variations. This paper provides multiple local feature representa...
متن کاملCombinational neural network using Gabor filters for the classification of handwritten digits
A classification algorithm that combines the components of k-nearest neighbours and multilayer neural networks has been designed and tested. With this method the computational time required for training the dataset has been reduced substancially. Gabor filters were used for the feature extraction to ensure a better performance. This algorithm is tested with MNIST dataset and it will be integrat...
متن کاملRobust CNN-based speech recognition with Gabor filter kernels
As has been extensively shown, acoustic features for speech recognition can be learned from neural networks with multiple hidden layers. However, the learned transformations may not sufficiently generalize to test sets that have a significant mismatch to the training data. Gabor features, on the other hand, are generated from spectro-temporal filters designed to model human auditory processing....
متن کامل