2.?BackgroundThe background of this work refers mainly to the design of embedded vision systems and the application and benefits of the use of LUTs for image segmentation.2.1. Embedded Vision SystemsRecent advances in computers and the improvement in micro-fabrication technology have fostered the design of tiny embedded systems with onboard electronics and sensors that also incorporates image-processing capabilities. For example, in [4], a versatile low cost embedded vision platform was presented to find blobs of a specific color in an image and also perform JPEG compression, frame differentiation, edge detection, image convolution, face detection, and color histogram computation. This embedded system was based on a low-cost CMOS color camera module, a frame buffer chip, and a low-cost microcontroller that processes all the images acquired and which was the inspiration for this work. Additionally, in [8], an intelligent embedded vision system to implement selleck chemicals llc different image filters and perform image correlation and transformation at up to 667 frames per second was proposed. In [9], an embedded vision system was proposed specifically for mobile robot navigation and low power consumption. This embedded system accelerates the basic image processing algorithms required in a mobile robot application, such as low-level image processing, spatial filtering, feature extraction, and block matching operations. In [10], a FPGA was proposed to process the images from a CMOS camera to create an embedded and autonomous image processing system. In [11], an FPGA was also proposed for integrated navigation by combining GPS, gyroscopes, and vehicle odometry. The proposal in [12] was an embedded palmprint recognition system based on the dual-core OMAP 3530 platform to achieve real-time performances. In [13], an embedded vision system was proposed for intelligent driver nighttime assistance and surveillance. The system integrated different devices in order to analyze nighttime vehicle detection, collision warning determination and traffic recording.2.2. Look-Up Tables for Fruit SegmentationIn a general application, fruit can be categorized by using different color features, for example by defining RGB thresholds [14�C16], by analyzing multispectral images [17], by computing the color distance to reference colors [18], by measuring color characteristics [19], by applying fuzzy logic [20] or neural networks [21], or by using LUTs [22,23]. The general use of LUTs has the advantage of reduced run-time computations because of the transformation of the input data into an output value of a range of index values.