An algorithm for mobile vision-based localization of skewed nutrition labels that maximizes specificity - Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition - page 225

1 Introduction
Many nutritionists and dieticians consider proactive nutrition management to be a key factor
in reducing and controlling cancer, diabetes, and other illnesses related to or caused by mis-
managed or inadequate diets. According to the U.S. Department of Agriculture, U.S. resid-
ents have increased their caloric intake by 523 calories per day since 1970. Mismanaged di-
ets are estimated to account for 30-35% of cancer cases [ 1 ] . A leading cause of mortality in
men is prostate cancer. A leading cause of mortality in women is breast cancer. Approxim-
ately 47,000,000 U.S. residents have metabolic syndrome and diabetes. Diabetes in children
appears to be closely related to increasing obesity levels. The current prevalence of diabetes
in the world is estimated to be at 2.8% [ 2 ] . It is expected that by 2030 the diabetes prevalence
number will reach 4.4%. Some long-term complications of diabetes are blindness, kidney fail-
ure, and amputations. Nutrition labels (NLs) remain the main source of nutritional informa-
tion on product packages [ 3 , 4 ] . Therefore, enabling customers to use computer vision on their
smartphones will likely result in a greater consumer awareness of the caloric and nutritional
content of purchased grocery products.
In our previous research, we developed a vision-based localization algorithm for hori-
zontally or vertically aligned NLs on smartphones [ 5 ] . The new algorithm, presented in this
chapter, improves our previous algorithm in that it handles not only aligned NLs but also
those that are skewed up to 35-40° from the vertical axis of the captured frame. Figure 1 shows
an example of such a skewed NL with the vertical axis of the captured frame denoted by a
white line. Another improvement designed and implemented in the new algorithm is the rap-
id detection of the presence of an NL in each frame, which improves the run time, because the
new algorithm fails fast and proceeds to the next frame from the video stream.
FIGURE 1 Skewed NL with vertical axis shown.
The new algorithm targets medium- to high-end mobile devices with single or quad-core
ARM systems. Since cameras on these devices capture several frames per second, the al-
gorithm is designed to minimize false positives rather than maximize true ones, because, at
such frequent frame capture rates, it is far more important to minimize the processing time
per frame.
Our chapter is organized as follows. In Section 2 , we present our previous work on ac-
cessible shopping and nutrition management to give the reader a broader context of the re-
search and development presented in this chapter. In Section 3 , we outline the details of our
algorithm. In Section 4 , we present the experiments with our algorithm and discuss our res-
ults. In Section 5 , we present our conclusions and outline several directions for future work.