Comparative analysis of several feature extraction methods in vehicle brand recognition

Lin, Shengmei; Zhao, Chihang; Qi, Xingzhi

doi:10.1109/icsenst.2016.7796337

Cited by 11 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Introduced in 2005 by Dalal and Trigg, the HOG is a feature descriptor used to detect objects [22], [26]. As can be observed in Fig.…”

Section: A Descriptors 1) Histogram Of Oriented Gradient Hog Featuresmentioning

confidence: 99%

“…Classifiers 1) Support Vector Machines (SVM). Was initially proposed by Cortes and Vapnik [26]. The principle of SVM classification is to find a hyper plane, which makes the classification of multidimensional space maximized.…”

Section: ) Speeded Up Robust Features (Surf)mentioning

confidence: 99%

“…2) K-nearest neighbor (kNN). Was proposed by Cover and Hart [26]. It is the extension of the minimum distance method and the nearest neighbor method.…”

Section: ) Speeded Up Robust Features (Surf)mentioning

confidence: 99%

“…Then it selects k training samples which are nearest to the testing sample x and counts the category of the k training samples selected. The testing sample belongs to the category which has the largest number of votes in the same category [4], [26].…”

Section: ) Speeded Up Robust Features (Surf)mentioning

confidence: 99%

See 3 more Smart Citations

Illumination Correction in a Comparative Analysis of Feature selection for Rear-View Vehicle Detection

Baghdadi¹,

Aboutabit²

2019

IJMLC

View full text Add to dashboard Cite

One of the most frequent infractions on the road is the act of a vehicle crossing to the wrong side of the road to pass another vehicle traveling in the same direction. Automatic detection of this violation can be a challenging issue. Thus, we aim to develop a computer vision system to robustly detect forbidden overtaking observed from a fixed camera. Our approach is based on two main phases: Line Detection and Vehicle Detection. In this work, we focus on the vehicle detection stage. Here, features are extracted from the image and then classified using machine learning algorithms. In a first experiment, we constructed different models using features such as HOG (Histogram of Oriented Gradient), SURF (Speeded up Robust Features), Gabor filter and LBP (Local Binary Patterns), and machine learning classifiers as SVM (Support Vector Machines), kNN (k-Nearest Neighbor) and Decision Tree. Then, we merged the best descriptors to combine the advantages of their different robustness in order to build a strong vehicle detection model. The performances of all constructed models are evaluated on the GTI database. In a second experiment, illumination normalization techniques were applied to image database for the effective models. Thus, the first experimental results reveal that the combination HOG+ LBP+ Gabor Phase performs well with SVM. The second experimental results show that the Variational Retinex algorithm-based illumination correction provides a significant improvement in the detection rate.

show abstract

“…Introduced in 2005 by Dalal and Trigg, the HOG is a feature descriptor used to detect objects [22], [26]. As can be observed in Fig.…”

Section: A Descriptors 1) Histogram Of Oriented Gradient Hog Featuresmentioning

confidence: 99%

Section: ) Speeded Up Robust Features (Surf)mentioning

confidence: 99%

“…2) K-nearest neighbor (kNN). Was proposed by Cover and Hart [26]. It is the extension of the minimum distance method and the nearest neighbor method.…”

Section: ) Speeded Up Robust Features (Surf)mentioning

confidence: 99%

Section: ) Speeded Up Robust Features (Surf)mentioning

confidence: 99%

See 2 more Smart Citations