Aesthetics in Digital Photography

Cover
Title Page
Copyright Page
Contents
Introduction: Image and Gaze
Chapter 1. The Legacy of Philosophers
1.1. The objectivist approach
1.1.1. The source: ancient Greece
1.1.2. After Greece
1.1.3. Kant and modern aesthetics
1.1.4. Objectivism after Kant: from pseudo-subjectivism to aesthetic realism
1.2. The subjectivist approach
1.2.1. From classicism to romanticism
1.2.2. The moderns
1.2.3. The influence of neurobiology
1.3. Subjectivism and objectivism: an ongoing debate
Chapter 2. Neurobiology or the Arbitrator of Consciousness
2.1. fMRI protocols and neuroaesthetics
2.2. The fMRI quest for “beauty processes” in the brain
2.2.1. The role of the prefrontal cortex
2.2.2. The role of the insular cortex
2.2.3. The role of the visual areas
2.2.4. The role of memory and cognition
2.2.5. The role of embodiment
2.3. Responses from functional electric encephalography
2.4. A global cognitive scheme for aesthetic judgment?
2.4.1. J. Petitot’s neurogeometric model
2.4.2. A. Chatterjee’s aesthetic emotion model
2.4.3. The model by Brown et al
2.4.4. Model proposed by H. Leder
2.4.5. The model by C. Redies
2.4.6. The emotions model developed by S. Koelsch et al.
2.4.7. L.H. Hsu’s model of emotions based on A. Damásio
2.4.8. Other models
2.5. A critique of neuroaesthetic methods
2.5.1. Criticism of neuroaesthetic methods
2.5.2. Criticisms of the objectives of neuroaesthetics
Chapter 3. What Are the Criteria For a Beautiful Photo?
3.1. Before we enter into the fray
3.1.1. What reference books do we have?
3.1.2. “Beauty of an image” or “quality of an image”?
3.1.3. A glossary of aesthetic appraisal
3.1.4. Measuring beauty
3.2. Composition
3.2.1. Complexity versus simplicity
3.2.2. Unity
3.2.3. A specific case in composition: landscapes
3.2.4. Using oculometry to analyze composition
3.2.5. Format or aspect ratio
3.2.6. The rule of thirds (RoT)
3.2.7. The center of the image
3.2.8. Other rules for composition
3.3. Histograms, spectral properties and textures
3.3.1. Histograms and gray levels
3.3.2. Focus, spectral density, fractals
3.3.3. Textures
3.4. Color
3.4.1. About the concept of color
3.4.2. Preferences related to isolated colors
3.4.3. Preferences related to color palettes
3.5. What behavioral psychosociology has to say
3.5.1. Images of nature
3.5.2. The aesthetics of faces
3.5.3. The role of the signature, title and context
3.5.4. Perception and memory: prototypicality
Chapter 4. Algorithmic Approaches to “Calculate” Beauty
4.1. First steps: C. Henry
4.2. G.D. Birkhoff’s mathematical approach
4.3. Those who followed G.D. Birkhoff
4.3.1. Beauty according to H.J. Eysenck
4.3.2. The Post-War years: the designers, A. Moles and M. Bense
4.3.3. A dynamic approach: P. Machado and A. Cardoso
4.3.4. Work carried out by J. Rigau, M. Feixas and M. Bert
4.4. Algorithmic approach with AI: J. Schmidhuber
Chapter 5. The Holy Grail of the Digital World: Artificial Intelligence
5.1. Which artificial intelligence?
5.1.1. The principles
5.1.2. Learning algorithms
5.2. Why artificial intelligence in aesthetics?
5.3. Expert opinions
5.4. The database
5.4.1. Generalist databases, used for aesthetic judgments
5.4.2. Databases that are specialized for aesthetic photography
5.4.3. Databases dedicated to artistic judgment
5.4.4. Other image databases that are sometimes used
5.4.5. Increasing databases
Chapter 6. Primitive-based Classification Methods
6.1. Judging aesthetics
6.1.1. Multimedia primitives: the ACQUINE system (Datta et al.)
6.1.2. Edges and chromatic distance: Ke et al.
6.1.3. Photography rules: Luo and Tang and Mavridaki and Mezaris
6.1.4. High-level primitives: Dhar et al.
6.1.5. Generic descriptors of vision: Marchesotti et al.
6.2. Help in composing beautiful photos
6.2.1. The library of aesthetic primitives developed by Su et al.
6.2.2. The OSCAR system by Yao et al.
6.2.3. Embedded systems: Lo et al. and Wang et al.
6.3. Some specific research related to the evaluation of aesthetics using primitives
6.3.1. Color harmony: Lu et al.
6.3.2. Group photography: Wang et al.
6.3.3. Social networks and crowdsourcing: Schifanella et al.
6.3.4. Looking at comments: San Pedro et al.
Chapter 7. Deep Neural Network Systems
7.1. DNNs dedicated to aesthetic evaluation
7.1.1. High and low resolutions: the RAPID system, Lu et al.
7.1.2. The multi-path DMA-Net architecture: Lu et al.
7.1.3. Adapting to the size of the image: Mai et al.
7.1.4. Finding beauty on the Web: Redi et al.
7.1.5. Siamese and GAN networks: Kong et al. and Deng et al.
7.1.6. Paying attention to the image construction: A-Lamp
7.2. Variants around the basic DNN architecture
7.2.1. Comparing photos between themselves: Schwarz et al.
7.2.2. Making use of knowledge of the subject: Kao et al.
7.2.3. BDN: halfway between classification and DNN
7.2.4. Using the distribution of the evaluations
7.2.5. Extracting a “dramatic” image from a panorama: the Creatism system
7.3. Written appraisals: analyzing them and formulating new ones
7.3.1. Photo critique captioning dataset (PCCD)
7.3.2. Neural aesthetic image retriever (NAIR)
7.3.3. Semantic processing by Ghosal et al.
7.3.4. Aesthetic multi attribute network (AMAN)
7.4. Measuring subjective beauty
7.4.1. Recommendation systems
7.4.2. Defining the user’s psychological profile
7.4.3. Learning the user’s tastes through tests
7.4.4. Multiplying concurrent expertise
Chapter 8. A Critical Analysis of Machine Learning Techniques
8.1. The popularity of studies on aesthetics
8.2. A summary of learning methods
8.2.1. Which architecture? Which software?
8.2.2. What performances?
8.3. Questioning the hypotheses
8.4. Specific features of beautiful images detected by a computer
8.4.1. Some observations on the photos in the AVA database
8.4.2. The scores in the AVA database
Conclusion
Appendix 1. A Brief Review of Aesthetics
Appendix 2. Aesthetics in China
Appendix 3. The Aesthetic of Persian Miniatures
Appendix 4. Aesthetics in Japan
References
Index
EULA