Fast object detection based on color histograms and local binary patterns

Lee, Kwon; Lee, Chulhee; Kim, Seon-Ae; Kim, Young-Hoon

doi:10.1109/tencon.2012.6412323

Cited by 23 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A first class of approaches is the countingby-detection methods [41], which formulate the problem as a detection task. Typical solutions rely on local features, such as histogram of oriented gradients (HOG) [9,12], local binary patters [8], or shape [22]. Nevertheless, leaf detection is a challenging task, since leaf surface is almost featureless and shape information is unreliable under heavy occlusion, as it can be seen in Figure 1.…”

Section: Related Workmentioning

confidence: 99%

Learning to Count Leaves in Rosette Plants

Giuffrida¹,

Minervini²,

Tsaftaris³

2015

Procedings of the Proceedings of the Computer Vision Problems in Plant Phenotyping Workshop 2015

121

View full text Add to dashboard Cite

Counting the number of leaves in plants is important for plant phenotyping, since it can be used to assess plant growth stages. We propose a learning-based approach for counting leaves in rosette (model) plants. We relate image-based descriptors learned in an unsupervised fashion to leaf counts using a supervised regression model. To take advantage of the circular and coplanar arrangement of leaves and also to introduce scale and rotation invariance, we learn features in a log-polar representation. Image patches extracted in this log-polar domain are provided to K-means, which builds a codebook in a unsupervised manner. Feature codes are obtained by projecting patches on the codebook using the triangle encoding, introducing both sparsity and specifically designed representation. A global, per-plant image descriptor is obtained by pooling local features in specific regions of the image. Finally, we provide the global descriptors to a support vector regression framework to estimate the number of leaves in a plant. We evaluate our method on datasets of the Leaf Counting Challenge (LCC), containing images of Arabidopsis and tobacco plants. Experimental results show that on average we reduce absolute counting error by 40% w.r.t. the winner of the 2014 edition of the challenge -a counting via segmentation method. When compared to state-of-the-art density-based approaches to counting, on Arabidopsis image data ∼75% less counting errors are observed. Our findings suggest that it is possible to treat leaf counting as a regression problem, requiring as input only the total leaf count per training image.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning to Count Leaves in Rosette Plants

Giuffrida¹,

Minervini²,

Tsaftaris³

2015

Procedings of the Proceedings of the Computer Vision Problems in Plant Phenotyping Workshop 2015

121

View full text Add to dashboard Cite

show abstract

“…It can be draw out for N-dimensions i.e. for each color present in the image but the three main colors usually are taken into account are Red, Green and Blue [6]. In Colored images 24 Bits are required to correspond the intensity value of each pixel, each 8 bit is used to store the intensity value of Red, Green, and Blue pixels respectively.…”

Section: Color Histogrammentioning

confidence: 99%

Orientation Invariant Object Recognitions Using Geometric Moments Invariants and Color Histograms

Samad¹,

Haq²,

Khan³

2015

IJCEE

View full text Add to dashboard Cite

Abstract:Object recognition is a very challenging task in artificial intelligence and robotics. Many approaches have been implemented to achieve this task with greater precision and accuracy. In this paper we have implemented the approach of detecting objects in images undergo with the change in scale, rotation, and orientation. Extracting Geometric moments invariant which are extensively use to extort global features and using color histogram approach we have improved the previously recognition rate to a significant measure. The accuracy of classification is increased by adding the new feature of color Histogram which is also an invariant feature for change in scale rotation, translation, and orientation of objects and using support vector machine learning algorithm for classification.

show abstract

“…For third step, we needed to calculate head and body ratio by equation (1). The main reason of this calculation is that people's head height becomes relatively smaller than body height while they grow up.…”

Section: Proposed Algorithmmentioning

confidence: 99%

“…One of the most significant stages of object detection is feature selection. To make impeccable real time object detection, features need to be robust, differential, and easy to calculate [1].…”

Section: Introductionmentioning

confidence: 99%

Child and Adult Classification Using Ratio of Head and Body Heights in Images

İnce¹,

Park²,

Song³

et al. 2014

IJCCE

View full text Add to dashboard Cite

Pedestrian detection is a challenging problem. There are various researches to detect people in digital images. Besides, to recognize children from adults in digital platforms is helpful for applications which are created to people's good account. For instance, if Closed Circuit Television (CCTV) which is located on traffic lamb detects child who is walking through pedestrian way, system could make some adjustment in a good way. Aim of this article is to detect children and adults separately in digital images. While we employed our method, we applied Haar Cascades which is widely used technique in object detection. At first, we detected head and full body of pedestrians, then we used relative measurements. So we did proportioning head size to body size of pedestrians. By this technique, we tried to discriminate children and adults. Our results were not %100 accurate but it gave a clue to improve ourselves. It seems that it's improvable for now. Index Terms-Absolute measurement, adult and child classification, Haar-like feature, pedestrian detection, relative measurements.

show abstract

Fast object detection based on color histograms and local binary patterns

Cited by 23 publications

References 12 publications

Learning to Count Leaves in Rosette Plants

Learning to Count Leaves in Rosette Plants

Orientation Invariant Object Recognitions Using Geometric Moments Invariants and Color Histograms

Child and Adult Classification Using Ratio of Head and Body Heights in Images

Contact Info

Product

Resources

About