Efficient Encoding Of Local Shape: Features For 3-D Object Recognition

1989 ◽  
Author(s):  
Paul G. Gottschalk ◽  
Trevor Mudge
Author(s):  
Anupam K. Gupta ◽  
Yanqing Fu ◽  
Dane Webster ◽  
Rolf Müller

Baffle shapes are commonly used in engineered devices to interface sound sources with the free field. Examples are acoustic horns seen in megaphones and horn-loaded loudspeakers. Typical for these devices are simple, static shapes that serve primarily an impedance-matching function. Diffracting baffles linked to a sound source are also common in the biosonar system of bats. In particular in bat groups that emit their ultrasonic pulses nasally, the nostrils are always surrounded by some baffle shape. This is the case across several large and diverse bat families such as horseshoe bats (Rhinolophidae), Old World leaf-nosed bats (Hipposideridae), and New World leaf-nosed bats (Phyllostomidae). However, biosonar baffles differ from their technical counterparts in two important ways: They typically have a much greater geometrical complexity and they are capable of non-rigid shape changes over time. Although simple horn shapes can be found in the noseleaves of many bat species, they are rarely as plain and regular as in megaphones and other technical applications of acoustical horns. Instead, the baffles are broken up into several parts that are frequently augmented with intricate local shape features such as ridges, furrows, and spikes. Furthermore, we have observed that in species belonging to the horseshoe bats and the related Old World leaf-nosed bats these local shape features are often not static, but can undergo displacements as well as non-rigid deformations. At least some of these dynamic effects are not passive byproducts of e.g., sound production or exhalation, but due to specific muscular actuation that can be controlled by the animals. To study these intricate, dynamic baffles as inspirations for smart structures, we have recreated the degrees of freedoms that Old World leaf-nosed bats have in deforming their noseleaves in a digital model using computer animation techniques. In its current form, our model has 6 degrees of freedom that can be used to test interactions between different motions using actuation patterns that occur in life as well as patterns that have not been observed, but could aid understanding. Because of the high-dimensional parameter space spanned by the different degrees of freedom, a high-performance computing platform has been used to characterize the acoustic behavior across a larger number of deformed no seleaf shapes. A physical test bed is currently under construction for implementing baffle motions that have been found to result in interesting changes of the acoustic device characteristics and could hence be of use to engineering applications.


Author(s):  
Aswathi A S ◽  
Philumon Joseph

The images have to be described by certain features. The shape is an important visual feature in understanding an image, that remains stable in spite of changes in an object's illumination, color, and texture. So shape features have been applied in object recognition tasks. There are many shape description and recognition techniques in the literature. This survey paper provides an overview of description and recognition techniques and examines implementation procedures for each technique and its advantages and disadvantages. Finally, identify some techniques for image retrieval according to standard principles.


2012 ◽  
Vol 132 (3) ◽  
pp. 1895-1895
Author(s):  
Mittu Pannala ◽  
Sajjad Z. Meymand ◽  
Rolf Mueller
Keyword(s):  

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2910 ◽  
Author(s):  
Jiajun Zhuang ◽  
Chaojun Hou ◽  
Yu Tang ◽  
Yong He ◽  
Qiwei Guo ◽  
...  

The maturity stage of bananas has a considerable influence on the fruit postharvest quality and the shelf life. In this study, an optical imaging based method was formulated to assess the importance of different external properties on the identification of four successive banana maturity stages. External optical properties, including the peel color and the local textural and local shape information, were extracted from the stalk, middle and tip of the bananas. Specifically, the peel color attributes were calculated from individual channels in the hue-saturation-value (HSV), the International Commission on Illumination (CIE) L*a*b* and the CIE L*ch color spaces; the textural information was encoded using a local binary pattern with uniform patterns (UP-LBP); and the local shape features were described by histogram of oriented gradients (HOG). Three classifiers based on the naïve Bayes (NB), linear discriminant analysis (LDA) and support vector machine (SVM) algorithms were adopted to evaluate the performance of identifying banana fruit maturity stages using the different optical appearance features. The experimental results demonstrate that overall identification accuracies of 99.2%, 100% and 99.2% were achieved using color appearance features with the NB, LDA and SVM classifiers, respectively; overall accuracies of 92.6%, 86.8% and 93.4% were obtained using local textural features for the three classifiers, respectively; and overall accuracies of only 84.3%, 83.5% and 82.6% were obtained using local shape features with the three classifiers, respectively. Compared to the complicated calculation of both the local textural and local shape properties, the simplicity and high accuracy of the peel color property make it more appropriate for identifying banana fruit maturity stages using optical imaging techniques.


2016 ◽  
Vol 321 ◽  
pp. 1135-1141 ◽  
Author(s):  
Guo-Jia Hou ◽  
Xin Luan ◽  
Da-Lei Song ◽  
Xue-Yan Ma

Author(s):  
Muhammad Attamimi ◽  
Djoko Purwanto ◽  
Rudy Dikairono

Sign in / Sign up

Export Citation Format

Share Document