Learned vs. Hand-Crafted Features for Pedestrian Gender Recognition

Antipov, Grigory; Berrani, Sid-Ahmed; Ruchaud, Natacha; Dugelay, Jean‐Luc

doi:10.1145/2733373.2806332

Cited by 97 publications

(63 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several works show, that on small-scale datasets with homogenous distribution, performance of handcrafted features can be considered on a par with learned ones. Whereas increased and more heterogeneous datasets lead to superiority of CNNs (Antipov et al, 2015;Fischer et al, 2014). Since we are crawling Street View images, we effectively have a vast amount of training data available -our limiting factor is the availability of correct ground truth for the building use.…”

Section: Street-view Based Image Classificationmentioning

confidence: 99%

Processing of Crawled Urban Imagery for Building Use Classification

Tutzauer¹,

Haala²

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Recent years have shown a shift from pure geometric 3D city models to data with semantics. This is induced by new applications (e.g. Virtual/Augmented Reality) and also a requirement for concepts like Smart Cities. However, essential urban semantic data like building use categories is often not available. We present a first step in bridging this gap by proposing a pipeline to use crawled urban imagery and link it with ground truth cadastral data as an input for automatic building use classification. We aim to extract this city-relevant semantic information automatically from Street View (SV) imagery. Convolutional Neural Networks (CNNs) proved to be extremely successful for image interpretation, however, require a huge amount of training data. Main contribution of the paper is the automatic provision of such training datasets by linking semantic information as already available from databases provided from national mapping agencies or city administrations to the corresponding façade images extracted from SV. Finally, we present first investigations with a CNN and an alternative classifier as a proof of concept.

show abstract

Section: Street-view Based Image Classificationmentioning

confidence: 99%

Processing of Crawled Urban Imagery for Building Use Classification

Tutzauer¹,

Haala²

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…For the gender detection evaluation, we use a pre-trained gender detection method by bodies using Convolutional Neural Networks (CNN), published in [2]. We evaluate this tool over 1081 videos from the HID database [19], including 864 male videos and 220 female videos.…”

Section: Algorithm Baselinesmentioning

confidence: 99%

“…if mc > 0.5, the gender is predicted as a male otherwise as a female). We apply the gender classifier [2] over the original videos and on the videos where the pixelization, Gaussian blur and body shape filters are applied. The accuracy of the classifier on the original body images is 81 %.…”

Section: Algorithm Baselinesmentioning

confidence: 99%

See 1 more Smart Citation

De-genderization by body contours reshaping

Ruchaud

Dugelay

2017

2017 IEEE International Conference on Identity, Security and Behavior Analysis (ISBA)

Self Cite

View full text Add to dashboard Cite

This paper deals with privacy protection in video surveillance. More specifically, the main goal of this work is to make the gender of people no more recognizable while preserving enough information concerning body shape and motion of people for action classification. We denote this processing as de-genderization. Regarding the current state-of-art methods, most of them have privacy filters only dedicated to de-identify people. These methods do not automatically imply the suppression of visual semantic traits such as gender. Therefore, we propose two approaches that modify the visual appearance of the body shape in order to de-genderize people while keeping the possibility to interpret the video. In both methods we start by extracting the contour points attached to the body shape of people in videos. Then we either mix the coordinates of the body shape and a predefined model, or we smooth the body shape by successive polygonal approximations based on convexity. Our results demonstrate that both proposed approaches protect the gender information while preserving the global body movement. The second approach based on convexity better preserves the visibility of human activities.

show abstract

“…37, we employ a convolutional neural network for gender recognition. In particular, we adopt an architecture proposed by Krizhevsky et al 45 This architecture is presented in Figure 4.…”

Section: Cnn-based Gender Recognitionmentioning

confidence: 99%

The impact of privacy protection filters on gender recognition

Ruchaud

Antipov

Korshunov

et al. 2015

Applications of Digital Image Processing XXXVIII

Self Cite

View full text Add to dashboard Cite

Deep learning-based algorithms have become increasingly efficient in recognition and detection tasks, especially when they are trained on large-scale datasets. Such recent success has led to a speculation that deep learning methods are comparable to or even outperform human visual system in its ability to detect and recognize objects and their features. In this paper, we focus on the specific task of gender recognition in images when they have been processed by privacy protection filters (e.g., blurring, masking, and pixelization) applied at different strengths. Assuming a privacy protection scenario, we compare the performance of state of the art deep learning algorithms with a subjective evaluation obtained via crowdsourcing to understand how privacy protection filters affect both machine and human vision.

show abstract

Learned vs. Hand-Crafted Features for Pedestrian Gender Recognition

Cited by 97 publications

References 12 publications

Processing of Crawled Urban Imagery for Building Use Classification

Processing of Crawled Urban Imagery for Building Use Classification

De-genderization by body contours reshaping

The impact of privacy protection filters on gender recognition

Contact Info

Product

Resources

About