ТОП просматриваемых книг сайта:
Handbook of Intelligent Computing and Optimization for Sustainable Development. Группа авторов
Читать онлайн.Название Handbook of Intelligent Computing and Optimization for Sustainable Development
Год выпуска 0
isbn 9781119792628
Автор произведения Группа авторов
Издательство John Wiley & Sons Limited
The proposed approach was evaluated by measuring the effectiveness of the detection of active garments and the identification of garments of interest.
Figure 3.4 Samples from the dataset.
Table 3.2 Precision and recall of active garment detection.
| Precision (%) | Recall (%) |
| 87.36 | 85.92 |
The effectiveness of active garment detection was evaluated by measuring its precision and recall, which are shown in Table 3.2. These metrics have been calculated as follows:
(3.5)
(3.6)
where TP, TN, FP, and FN denote the true positive, true negative, false positive, and false negative observations, respectively.
The garments of interest were verified manually with estimations (as the actual ground truth for the degree to which an active garment is a garment of interest to the customers was not available due to the subjective nature of the task). Visual illustrations of the results obtained in different scenarios have been displayed in Figures 3.5 to 3.7. In these figures, a green box indicates a garment of interest, while a red box indicates an active garment which is not a garment of interest.
Figure 3.5 Identification of garment of interest in the presence of a single customer and a single active garment.
Figure 3.6 Identification of garments of interest in the presence of a single customer and multiple active garments.
Figure 3.7 Identification of garments of interest in the presence of multiple customers.
The variation in the average confidence scores taken at varying confidence thresholds (δ) for a garment of interest of a given color is illustrated in Figure 3.8. From this figure, it can be observed that the variation takes the form of an S-curve, which signifies that the average confidence score mimics a logistic curve. Using this knowledge, we can easily observe that the confidence threshold (δ) of 0.6 is an optimal value (i.e., when the curve starts to flatten immediately after the point of inflection) to classify whether an active garment is a garment of interest to a given customer. The average confidence score at this confidence threshold (δ) exceeds 0.8 for all the colors under observation. This ensures that the wrists of the interacting person are sufficiently close to the active garment.
Figure 3.8 Variation of average confidence score with respect to changes in confidence threshold for garments of interest of a given color.
The average confidence score obtained by garments of interest for each given color at a confidence threshold (δ) of 0.6 is illustrated in Figure 3.9. This figure indicates the average degree to which the customers found the garment of a given color interesting, thereby providing insights into the colors customers found the most and least interesting for the garments present in the store.
Figure 3.9 Average confidence score obtained by garments of interest of particular color at a confidence threshold of 0.60.
The distribution of the total duration of time for which the customers were interested in a garment of a given color at a confidence threshold (δ) of 0.6 is illustrated in Figure 3.10. This figure elucidates the distribution of the total time spent by the customers for each given color, thereby providing invaluable information about which color for a garment was most and least interacted with the customer base at the store.
3.4.3 Analysis of the Proposed Approach
It can be observed that the effectiveness of the proposed approach in detecting active garments depends on the foreground information extracted and the color masks applied subsequently. If the foreground information obtained after Stage 1 (refer to Figure 3.1) fails to capture an active garment, then the recall of the active garment detection is affected. Garments with consistent color and simple patterns were more accurately detected by the proposed approach as compared to garments with multiple colors and complex patterns. Active garments were partially detected in scenarios where the customer obstructed a major portion of the garment. The proposed approach was able to identify garments of interest well, especially when the garments and wrists of a customer are in clear view.
Figure 3.10 Total duration of time for which customers were interested in a garment of a given color at a confidence threshold of 0.60.
From the data displayed in Figures 3.9 and 3.10, we can make the following key observations:
1 1. Customers spent the most time interacting with various garments having shades of blue or green color,