دانلود رایگان مقاله انگلیسی + خرید ترجمه فارسی | |
عنوان فارسی مقاله: |
تشخیص جنسیت و قومیت از پروفایل های نیم رخ سایه صورت |
عنوان انگلیسی مقاله: |
Gender And Ethnicity Identification From Silhouetted Face Profiles |
|
مشخصات مقاله انگلیسی (PDF) | |
سال انتشار | 2009 |
تعداد صفحات مقاله انگلیسی | 4 صفحه با فرمت pdf |
رشته های مرتبط با این مقاله | مهندسی کامپیوتر |
گرایش های مرتبط با این مقاله | هوش مصنوعی و مهندسی الگوریتم ها و محاسبات |
چاپ شده در مجله (ژورنال) | شانزدهمین کنفرانس بین المللی IEEE در پردازش تصویر – 16th IEEE International Conference on Image Processing |
کلمات کلیدی | تشخیص چهره، تشخیص الگو و پردازش تصویر |
ارائه شده از دانشگاه | گروه مهندسی برق و کامپیوتر، ایالات متحده آمریکا |
رفرنس | دارد ✓ |
کد محصول | F999 |
نشریه | آی تریپل ای – IEEE |
مشخصات و وضعیت ترجمه فارسی این مقاله (Word) | |
وضعیت ترجمه | انجام شده و آماده دانلود |
تعداد صفحات ترجمه تایپ شده با فرمت ورد با قابلیت ویرایش | 7 صفحه با فونت 14 B Nazanin |
ترجمه عناوین تصاویر و جداول | ترجمه شده است ✓ |
ترجمه متون داخل تصاویر | ترجمه نشده است ☓ |
ترجمه متون داخل جداول | ترجمه نشده است ☓ |
درج تصاویر در فایل ترجمه | درج شده است ✓ ☓ |
درج جداول در فایل ترجمه | درج شده است ✓ |
درج فرمولها و محاسبات در فایل ترجمه | به صورت عکس درج شده است ✓ |
منابع داخل متن | درج نشده است ☓ |
کیفیت ترجمه | کیفیت ترجمه این مقاله متوسط میباشد |
توضیحات | ترجمه این مقاله به صورت خلاصه انجام شده است. |
فهرست مطالب |
چکیده
1- مقدمه
2- پس زمینه
3- دیتابیس
4- زمینه شکل
5- تبدیل مختصات
6- روش شناسی
7-ازمایش و نتایج
8- مشاهدات و بحث
|
بخشی از ترجمه |
چکیده 1- مقدمه |
بخشی از مقاله انگلیسی |
ABSTRACT This paper demonstrates, to our best knowledge, the first attempt on gender and ethnicity identification from silhouetted face profiles using a computer vision technique. The results achieved, after testing on 441 images, show that silhouetted face profiles have a lot of information, in particular, for ethnicity identification. Shape context based matching [1] was employed for classification. The test samples were multi-ethnic. Average accuracy for gender was 71.20% and for ethnicity 71.66%. However, the accuracy was significantly higher for some classes, such as 83.41% for females (in case of gender identification) and 80.37% for East and South East Asians (in case of ethnicity identification). 1. INTRODUCTION Gender and Ethnicity identification present yet another challenge in face processing. These have an increasing number of applications as Human-Computer Interaction (HCI) and visual surveillance technologies evolve. Gender identification can be useful in face recognition, as this shall reduce the problem of matching the face with half of the database (provided both the genders have equal probability of occurrence in the database). Ethnicity identification shall reduce this problem even further (provided the database is multi-ethnic). In HCI, for instance, the computer can adapt to a person’s sex in terms of processing (e.g.) the person’s voice or offering the person the options which may be more specific and useful to a particular gender, etc. These may also aid shopkeepers; for example, to know the demographic distribution of the customers over a period of time. In the following sections, we’ll present the novelty of this paper, description of the database, experimental setup and finally the results and discussion. Please note that the terms race and ethnicity, in this paper, refer to a group of people who share similar facial features, which perceptually distinguish them from other groups (ethnicities). 2. BACKGROUND Humans are very accurate in deciding the gender of a face even when cues from makeup, hairstyle and facial hair are minimized [2]. The results from [3] show that both the color and shape are vital in deciding the sex and race from a face by humans. Bruce et al. in [2] showed that the ‘average’ male face differs from an ‘average’ female face in the 3-D representation of the face (obtained by laser scanning), by having a more protuberant nose/brow and more prominent chin/jaw. Shape was also found important in race (ethnicity) decisions as shown in [3]. Davidenko in [4] reveals the presence of cues for humans, even in silhouetted face profiles, for gender identification. In a more recent study, Davidenko et al. [5] claimed that face silhouettes also have information for ethnicity identification. Most of the existing work in the computer vision community uses frontal face images for gender or ethnicity identification. Some examples of the existing literature on gender identification may be found in [6], [7], [8], [9], [10], [11], [12], [13], [14], [15], [16] and [17]; while for ethnicity identification may be found in [8], [11], [17], [18] and [19]. But none of the papers ever experimented with silhouetted face profiles. The aim of this paper is to exploit the information available in the silhouetted profile faces reported in [4] and [5]. This paper, to our best knowledge, demonstrates the first attempt for gender and ethnicity identification using silhouetted face profiles with any computer vision technique. In future, this may be fused with some other method. |