Carla Brambilla

Human Computer Interaction: Legibility and Contrast

In human computer interaction readability of textual information is one of the foremost requirements for displays designed to provide visual information. In this context it is of main interest to identify the design attributes that influence readability, and investigate their relationship with measures of ease of reading. In this paper we present results from a readability experiment focused on text contrast that we performed on the Web. Our analysis indicate that light text on dark background is more difficult to read, and that the minimum luminance contrast between foreground and background color, in terms of CIELAB lightness difference, should be about 27 units.

AUTOMATIC CLASSIFICATION OF DIGITAL PHOTOGRAPHS BASED ON DECISION FORESTS

Annotating photographs with broad semantic labels can be useful in both image processing and content-based image retrieval. We show here how low-level features can be related to semantic photo categories, such as indoor, outdoor and close-up, using decision forests consisting of trees constructed according to CART methodology. We also show how the results can be improved by introducing a rejection option in the classification process. Experimental results on a test set of 4,500 photographs are reported and discussed.

A hierarchical classification strategy for digital documents

The effective classification of image contents allows us to adopt strategies that can meet the increasing demand for quality, speed and ease of use in imaging applications. We report here on our experience in the use of CART classifiers for the classification of images indexed by low-level perceptual features such as color, texture, and shape. The problem addressed is the complex matter of distinguishing among photographs, graphics, texts, and compound documents. To cope with the great variety of compound documents we have designed a hierarchical classification strategy which first classifies images as compound or non-compound by verifying the homogeneity of the sub-images in terms of low-level features. Non-compound images are then classified as photographs, graphics, or texts. The results are reported and discussed.

On the detection of pornographic digital images

The paper addresses the problem of distinguishing between pornographic and non-pornographic photographs, for the design of semantic filters for the web. Both, decision forests of trees built according to CART (Classification And Regression Trees) methodology and Support Vectors Machines (SVM), have been used to perform the classification. The photographs are described by a set of low-level features, features that can be automatically computed simply on gray-level and color representation of the image. The database used in our experiments contained 1500 photographs, 750 of which labeled as pornographic on the basis of the independent judgement of several viewers.

A color selection tool for the readability of textual information on web pages

One of the issues in Web page design is the selection of appropriate combinations of background and foreground colors to display textual information. Colors have to be selected in order to guarantee legibility for different devices, viewing conditions and, more important, for all the users, including those with deficient color vision. In this paper we present a tool to select background and foreground colors for the display of textual information. The tool is based on the Munsell Book of Colors; it allows the browsing of the atlas and indicates plausible colors based on a set of legibility rules, which have been defined experimentally.

Controlled and uncontrolled viewing conditions in the evaluation of prints

Visual experiments, attesting visual preference, visual ranking and visual differentiation, are very important to academia and industry. They are traditionally performed into laboratories under controlled viewing conditions, resulting very costly in their execution, due to the time and effort involved by all participants. If controlled tests could be substituted by uncontrolled tests, a potential serious improvement could be obtained by eliminating a large part of the cost. In this work we investigate if, and to what extent, visual experiments performed under controlled viewing conditions can be substituted by uncontrolled experiments. A task of visual preference of prints is carried out. This task is performed in the laboratory, under controlled viewing conditions, and in many different places, under natural, artificial and mixed light. We observe statistical equivalence for preferences expressed in controlled or uncontrolled conditions that supports the hypothesis that visual preference can be assessed with uncontrolled tests.

Semantic labeling of digital photos by classification

The paper addresses the problem of annotating photographs with broad semantic labels. To cope with the great variety of photos available on the WEB we have designed a hierarchical classification strategy which first classifies images as pornographic or not-pornographic. Not-pornographic images are then classified as indoor, outdoor, or close-up. On a database of over 9000 images, mostly downloaded from the web, our method achieves an average accuracy of close to 90%.

Content-Based Classification of Digital Photos

Annotating images with a description of the content can facilitate the organization, storage and retrieval of image databases. It can also be useful in processing images, by taking into account the scene depicted, in intelligent scanners, digital cameras, photocopiers, and printers. We present here our experimentation on indoor/outdoor/close-up content-based image classification. More specifically, we show that it is possible to relate low-level visual features to semantic photo categories, such as indoor, outdoor and close-up, using tree classifiers. We have designed and experimentally compared several classification strategies, producing a classifier that can provide a reasonably good performance on a generic photograph database.

Content-based image classification

The effective classification of the contents of an image allows us to adopt the most appropriate strategies for image enhancement, color processing, compression, and rendering. We address here the problem of distinguishing photographs from graphics and texts purely on the basis of low-level feature analysis. The preliminary results of our experimentation are reported.

Comparing image preference in controlled and uncontrolled viewing conditions

We examine the relationship between controlled and uncontrolled visual preference tests. We compare the results for the preference of printed images in various viewing environments. The data are examined with regard to different numbers of observer subsets and we can derive an experimental guideline for an equivalence of the controlled and uncontrolled preference experiments based on the certainty of the expected result.