4. Photo semantics

colorful photos are low quality because professional photographers sometimes choose eliminating colors to express some feelings. As shown in Figure 12(a), the photo is colorful, while the photo in Figure 12(b) is achromatic, and they give different feelings. The degree of colorfulness of a photo is defined as the reciprocal of the achromatic feature that is a special color component feature because it comprises rare hue components and it is perceived as a grayscale

Figure 12. Two photos with different degrees of colorfulness: (a) more colorful; (b) more achromatic.

Professional photos are usually possessed of greater simplicity to make the subject appear more attractive. Figure 13(a) is simpler in terms of its color distribution whereas the color

The simplicity feature is computed from the color distribution of a photo. The formula for the

j{ ðx, yÞjChRðx, yÞ ¼ ChGðx, yÞ ¼ ChBðx, yÞ}j

width � height <sup>ð</sup>10<sup>Þ</sup>

f colorfulness ¼ 1=f achromatic ð11Þ

photo. The achromatic feature can be obtained from

width X x¼1

height X y¼1

Figure 13. Two photos with different degrees of simplicity: (a) simpler; (b) more complex.

f achromatic ¼

distribution of Figure 13(b) is rather complex.

simplicity feature [6] is expressed as

Then the degree of colorfulness yields

3.8. Simplicity

106 Perception of Beauty

A photo with some semantic meanings can be popular even if it lacks some aesthetic elements. For example, in a collection of photos captured by travelers, those with animals or human faces are usually more possibly preferred than those without them [9]. Figure 14 demonstrates the photo with some semantic meanings. In Figure 14(a), there are many human faces detected. Actually, people prefer to keep photos with faces, animals, and so on. Currently, some object detection methods, such as an AdaBoost algorithm, are able to detect photos with face, eyes, vehicles, and animals. However, most of the object detection methods work primarily on rigid objects. For nonrigid objects, in Figure 14(b), both the photo segmentation and visual word techniques [4] are adopted to classify the regions of a photo as certain elements, say sky, water, tree, grass, roads, or buildings.

Figure 14. The semantics of a photo: (a) faces found by object detection methods; (b) the photo layout found by segmentation and visual word techniques.
