Low Level Features for Quality Assessment of Facial Images

  title={Low Level Features for Quality Assessment of Facial Images},
  author={Arnaud Lienhard and Patricia Ladret and Alice Caplier},
An automated system that provides feedback about aesthetic quality of facial pictures could be of great interest for editing or selecting photos. [] Key Method 15 features that depict technical aspects of images such as contrast, sharpness or colorfulness are computed on different image regions (face, eyes, mouth) and a machine learning algorithm is used to perform classification and scoring.

Figures and Tables from this paper

Image Aesthetic Assessment: An experimental survey

This article systematically evaluates recent deep-learning settings that are useful for developing a robust deep model for aesthetic scoring and summarizes these approaches based on visual feature types (hand-crafted features and deep features) and evaluation criteria (data set characteristics and evaluation metrics).

How to predict the global instantaneous feeling induced by a facial picture?


This thesis investigates the use of deep convolutional neural network for automatic estimation of image quality and image aesthetics and proposes a method that outperformed state-of-the-art methods on the largest publicly available dataset.

Facial Image Aesthetics Prediction with Visual and Deep CNN Features

This work introduces a framework that uses deep face representations from CNNs and other visual features to tackle the problem of predicting the aesthetics of the facial image in stills, and outperformed the state-of-the-art in aesthetic prediction in portrait images.

The relative contributions of facial parts qualities to the face image utility

This work investigates the effects of face subregions (semantic contexts) and link the general image quality of faceSubregions with face image utility and applies four face image quality assessment methods on four face sub Regions and the aligned faces.

A Comprehensive Survey on Image Aesthetic Quality Assessment

A comprehensive survey on image aesthetic quality assessment, mainly focus on the contributions and novelties of the existing approaches recently, and reviewed recent applications concerning image aesthetics.

A Comprehensive Survey on Computational Aesthetic Evaluation of Visual Art Images: Metrics and Challenges

This survey presents a comprehensive listing of the reviewed works on aesthetic assessment of photographs and paintings, mainly highlighting the contributions and innovations of the existing approaches and systematically evaluating recent deep learning techniques that are useful for developing robust models for aesthetic prediction tasks.

Will the Machine Like Your Image?Automatic Assessment of Beauty in Images with Machine Learning Techniques †

The latest advances of computer methods that aim at computationally distinguishing high-quality from low-quality photos and images, relying on machine learning techniques are examined.

An Efficient Method for Face Quality Assessment on the Edge

This work proposes a face quality score regression by just appending a single layer to a face landmark detection network, and shows the proposed approach’sency through comparison with state-of-the-art face quality regression models on data sets and real-life scenarios.

Aesthetic Evaluation of Facial Portraits Using Compositional Augmentation for Deep CNNs

A new compositional-based augmentation scheme for aesthetic evaluation of portraits by well-known deep convolutional neural network (DCNN) models is introduced that takes into account compositional photographic rules to ensure that the aesthetic in portraits are not hindered by standard transformations used for DCNN models.



Photo rating of facial pictures based on image segmentation

This work focuses on the estimation of the image quality of facial portraits and it is shown that concerning facial picture rating, it is better to estimate each feature on the different picture parts (background and foreground).

Aesthetic quality assessment of headshots

A method built on most important rules or guidelines used by professional photographers to assess aesthetic quality of headshots, using popular machine learning algorithms, support vector machines and Real AdaBoost to determine whether a headshot is aesthetically appealing or unappealing.

Full Reference Image Quality Assessment Based on Saliency Map Analysis

This article proposes a mixed saliency map model based on Itti's model and face detection that shows that the performance of the image quality assessment on full subsets is enhanced.

Automated Aesthetic Analysis of Photographic Images

It is shown that aesthetic signatures can still be used to improve upon the current state-of-the-art in automatic aesthetic judgment, but also enable interesting new photo editing applications such as automated aesthetic analysis, HDR tone mapping evaluation, and providing aesthetic feedback during multi-scale contrast manipulation.

Automatic aesthetic value assessment in photographic images

Experiments over a consumer photographic image collection with user ground-truth indicate that the proposed algorithms provide promising results for automatic image aesthetic assessment.

Photo and Video Quality Evaluation: Focusing on the Subject

This paper first extracts the subject region from a photo, and then formulate a number of high-level semantic features based on this subject and background division, which achieves a precision of over 95% in a reasonable recall rate for both photo and video assessments.

Towards aesthetics: a photo quality assessment and photo selection system

The proposed system focuses on photos with faces, which constitute an important part of consumer photo albums, and proposes an aesthetics-based photo assessment algorithm, which differs from prior works by eliminating unimportant faces before optimizing photo composition.

The Design of High-Level Features for Photo Quality Assessment

  • Yan KeXiaoou TangFeng Jing
  • Computer Science
    2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
We propose a principled method for designing high level features forphoto quality assessment. Our resulting system can classify between high quality professional photos and low quality snapshots.

High level describable attributes for predicting aesthetics and interestingness

This paper demonstrates a simple, yet powerful method to automatically select high aesthetic quality images from large image collections and demonstrates that an aesthetics classifier trained on describable attributes can provide a significant improvement over baseline methods for predicting human quality judgments.

Evaluating photo aesthetics using machine learning

The results indicated that automatic aesthetic assessment is feasible, since the use of machine learning methods provided 95 per cent classification accuracy in reference to the overall ratings of photographs (9 per cent improvement relative to comparable research).