Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Face detection locates faces prior to various face-
related applications. The objective of face detecti
on is to
determine whether or not there are any faces in an
image and, if any, the location of each face is det
ected.
Face detection in real images is challenging due to
large variability of illumination and face appeara
nces.
This paper pro...
Contexts in source publication
Context 1
... Section 4 gives conclusions. Figure 1 shows the block diagram of the proposed face detection algorithm, which consists of five parts. At first, a whole input image is scanned by multiple local windows, because multiple faces of various sizes may exist at different positions in an input image. ...
Context 2
... performance of the proposed face detection is evaluated in terms of the numbers of FPs and TPs. Receiver operator characteristic (ROC) curve, which is a representative performance curve, shows the correlation between FP and TP by adjusting parameters of the face detection algorithm as shown in Figure 10. This paper compares the performance of the proposed face detection algorithm and three existing algorithms: adaboost algorithm [22], NN algorithm [18], and our previous algorithm [16]. ...
Context 3
... the NN algorithm, the number of learning data from CMU database [21] varies from 40 to 69 for face images and from 40 to 59 for non-face images. Figure 10 shows the result of ROC curve. It is observed that the proposed face detection algorithm is more effective than two existing algorithms if the number of FPs is larger than 180. ...
Context 4
... precision rate P is defined by (number of TPs)/(number of faces) and the recall rate R is defined by (number of TPs)/(number of TPs + number of FPs). The f-measure F is defined as When the number of FPs is larger than 100, f-measure of the proposed algorithm is larger than those of our previous algorithm, while larger than 200, f-measure of the proposed algorithm is larger than those of the adaboost, NN algorithm, and our previous algorithm, which is the same tendency observed from the ROC curve shown in Figure 10. Figure 11 shows test images containing a single face in Caltech database images, in which the left image is affected by dark illumination whereas the right one by the direction of illumination source. ...
Context 5
... f-measure F is defined as When the number of FPs is larger than 100, f-measure of the proposed algorithm is larger than those of our previous algorithm, while larger than 200, f-measure of the proposed algorithm is larger than those of the adaboost, NN algorithm, and our previous algorithm, which is the same tendency observed from the ROC curve shown in Figure 10. Figure 11 shows test images containing a single face in Caltech database images, in which the left image is affected by dark illumination whereas the right one by the direction of illumination source. Figure 12 shows simulation results using parameters in which 600 FPs are detected in 450 face images. ...
Context 6
... f-measure F is defined as When the number of FPs is larger than 100, f-measure of the proposed algorithm is larger than those of our previous algorithm, while larger than 200, f-measure of the proposed algorithm is larger than those of the adaboost, NN algorithm, and our previous algorithm, which is the same tendency observed from the ROC curve shown in Figure 10. Figure 11 shows test images containing a single face in Caltech database images, in which the left image is affected by dark illumination whereas the right one by the direction of illumination source. Figure 12 shows simulation results using parameters in which 600 FPs are detected in 450 face images. If these images are used to detect face images by the adaboost and NN algorithm, faces are not detected well, as shown in Figures 12(a) and 12(b), respectively. ...
Context 7
... 12 shows simulation results using parameters in which 600 FPs are detected in 450 face images. If these images are used to detect face images by the adaboost and NN algorithm, faces are not detected well, as shown in Figures 12(a) and 12(b), respectively. However, the our previous algorithm [16] and proposed algorithm detect faces well, as shown in Figures 12(c) and 12(d), respectively, because of the illumination change correction. ...
Context 8
... these images are used to detect face images by the adaboost and NN algorithm, faces are not detected well, as shown in Figures 12(a) and 12(b), respectively. However, the our previous algorithm [16] and proposed algorithm detect faces well, as shown in Figures 12(c) and 12(d), respectively, because of the illumination change correction. [16], and (d) the proposed algorithm. ...
Context 9
... and (d) the proposed algorithm. Figure 13 shows test images containing multiple faces in real images, in which the left and right image are affected by the direction of illumination source in outdoor and indoor environment, respectively. Figure 14 shows simulation results using parameters in which 200 FPs are detected in 450 face images. ...
Context 10
... 13 shows test images containing multiple faces in real images, in which the left and right image are affected by the direction of illumination source in outdoor and indoor environment, respectively. Figure 14 shows simulation results using parameters in which 200 FPs are detected in 450 face images. The result shows that the adaboost, NN, and our previous algorithm [16] either do not detect faces with FPs or do detect face with FPs, as shown in Figures 14(a), 14(b), and 14(c), respectively. ...
Context 11
... 14 shows simulation results using parameters in which 200 FPs are detected in 450 face images. The result shows that the adaboost, NN, and our previous algorithm [16] either do not detect faces with FPs or do detect face with FPs, as shown in Figures 14(a), 14(b), and 14(c), respectively. However, the proposed face detection algorithm does detect all faces without FP, as shown in Figure 14(d). ...
Context 12
... result shows that the adaboost, NN, and our previous algorithm [16] either do not detect faces with FPs or do detect face with FPs, as shown in Figures 14(a), 14(b), and 14(c), respectively. However, the proposed face detection algorithm does detect all faces without FP, as shown in Figure 14(d). However, the proposed face detection algorithm incorrectly detects some faces with mustache around the mouth, because mustache affects the gradient distribution. ...
Similar publications
In general, tunnel analyses are complex engineering tasks. This is mainly due to non‐linear effects determining the overall loadbearing behaviour (even under service load conditions) because no clear separation between action and resistance is possible (safety concept) plus a series of interdependencies and interaction effects that must not be negl...
![Figure 3. Geometric parameters of a compound channel [24].](profile/Zohreh_Sheikh_Khozani/publication/310490120/figure/fig2/AS:468968679972866@1488822254763/Geometric-parameters-of-a-compound-channel-24_Q320.jpg)
The ability of five different methods to estimate the shear stress distribution in compound channels is investigated. Methods proposed by Yang and Lim (YLM), Khodasheans and Paquier (KPM), Sterling and Knight (SKM), Zarrati et al. (ZAM), and Bonakdari et al. (BAM) are compared with experimental data. YLM and KPM did not provide reliable results as...
This study aimed to examine the relationship of mathematics literacy self-efficacy perceptions of preschool teachers with geometric shape recognition and number skills of children using structural equation modelling. The descriptive study adopted a relational screening model. The study sample comprised 9 teachers and 103 children selected by maximu...
pl S t r e s z c z e n i e. Przedstawiono przykładowe podejście do oceny rzetelności wyników badań, przy wykorzystaniu statystycznych metod obliczeniowych. Procedurę oceny rzetelności wyników pomiarów wykonano modelowo dla cech geometrycznych nasion fasoli mierzonych, przy wykorzy-staniu różnych przyrządów pomiarowych (suwmiarek: analogowej i cyfro...
Citations
... Face detection / recognition is achieved in many ways. A geographical face model proposed by Kang-Seo et al. [9] uses images of gradient magnitude including an algorithm for face detection from 33 block rank pattern of images. Experiments conducted proved that the method is robust in face detection and performs better to illumination changes. ...
User Profiling in Online Social Network (OSN) requires the frontal photographs of the users as thier Profile Pictures in Multi-Social Networking. The existing algorithms are ineffective in detecting the facial features like eyes, mouth and nose on the face appropriately, making it inefficient. This work proposes a novel approach to efficiently detect the facial features and improve the effectiveness of face detection and recognition by bifurcating the detected face horizontally, vertically and cropping it. The algorithm is effectively run only on the portion of the detected face Bounded Box (BB) and area to generate bounded boxes of other facial objects and later the Euclidian Distance (ED) between those BBs with respect to that of the face is computed to get Logarithm of Determinant of Euclidian Distance Matrix (LDEDM) in Relative-Distance (RD) method and stored in the database. The LDEDM so computed is unique for every user under consideration and is further utilized for identity matching recognizing from the database. The results show that the Equal Error Rate (EER) is considerably low indicating accurate threshold fixation for better performance with the proposed Relative Distance based User Profiling from Profile Picture (RDUP3) algorithm.
... For this purpose, by using gradient magnitude images, Kang-Seo et al. [102] have proposed a geographical face model. Geographically the existence of face is identified and by using 33 block rank patterns face detection algorithm, face in the given image is detected and even for the illumination changes, the method performs better. ...
Advances in Online Social Networks is creating huge data day in and out providing lot of opportunities to its users to express their interest and opinion. Due to the popularity and exposure of social networks, many intruders are using this platform for illegal purposes. Identifying such users is challenging and requires digging huge knowledge out of the data being flown in the social media. This work gives an insight to profile users in online social networks. User Profiles are established based on the behavioral patterns, correlations and activities of the user analyzed from the aggregated data using techniques like clustering, behavioral analysis, content analysis and face detection. Depending on application and purpose, the mechanism used in profiling users varies. Further study on other mechanisms used in profiling users is under the scope of future endeavors.
... Kang-Seo et al. [5] proposed aa algorithm to detect face using 33 block rank patterns of gradient magnitude images and a geometrical face model. Experiments show that their method is robust to illumination changes. ...
Profiling Online Social Network (OSN) Users by matching their Profile Pictures in Multi-Social Networking requires their own frontal face images in consideration. Present State-of-the-Art algorithms are ineffective in detecting mouth and nose on the face, making it inefficient to be used in matching different faces by localizing their facial features. This work proposes a novel approach to improve the effectiveness and efficiency of face detection by bifurcating the detected face horizontally and vertically. The algorithm runs only on the portion of the detected face Bounded Box (BB) to generate bounded boxes of other facial objects, and later the Euclidian distance between the BBs with respect to that of the face is computed to get Logarithm of Determinant of Euclidian Distance Matrix (LDEDM) in Relative-Distance method and stored in the database. The LDEDM so computed is unique for the user image under consideration and is used for the purpose of matching the identity of the user images from the database. The Equal Error Rate (EER) is considerably low with the proposed User Profiling from Profile Picture (UP3) algorithm indicating better performance.
