JPH012179A - How to identify food - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

DETAILED DESCRIPTION OF THE INVENTION [Industrial Field of Application] The present invention relates to a food identification method suitable for use in identifying types of dried vegetables and the like.

[Prior art and its problems]

In general, the color of dried vegetables such as chopped cabbage, green onions, and carrots (instant ramen ingredients, etc.) is also an important factor in terms of commercial value. For example, cabbage harvested in the summer is green, but cabbage harvested in the winter is relatively yellow. For this reason, it is often necessary to supply cabbage with a desired color or mix cabbage from different harvest periods in an appropriate ratio to obtain a desired color.

By the way, in such a case, it is very difficult to determine which of the desired types or in what proportions should be mixed to obtain the desired color.

For this reason, conventional methods relied on visual inspection by an expert, but accurate identification was difficult due to the sensory nature of the technique. In addition, attempts have been made to identify using expensive color difference meters that can measure hue, saturation, etc. with high precision, but in the case of dried vegetables with variable color patterns, the high precision results in poor reproducibility and the identification accuracy is reduced. There were problems such as deterioration that made it impractical.

[Means for solving problems]

The present invention aims to provide a novel food identification method that solves the problems existing in the prior art, and is achieved by the method described below.

That is, the food identification method according to the present invention images a food such as a single type or a mixture of multiple types of dried vegetables V, and converts the brightness of pixels obtained from a certain area into numerical values, for example, by dividing the brightness by a preset level S. It is characterized in that the type of food is identified by the number of pixels in the - direction.

〔Example〕

Hereinafter, preferred embodiments of the present invention will be described in detail based on the drawings.

FIG. 1 is a block system diagram of an identification device capable of implementing the method of the present invention, FIG. 2 is an external perspective view of an imaging unit in the identification device, and FIG. 3 is a pattern showing an example of a binarized image in the identification device. FIG. 4 is a diagram showing the relationship between the number of pixels and the mixing ratio of different types of dried vegetables.

By the way, in this identification method, an object whose color should originally be identified is identified by detecting brightness. In other words, in the case of a single dried vegetable or a mixture of multiple types of dried vegetables, it can be visually recognized as a color pattern in which chopped vegetables of a negative color and chopped vegetables of other colors are mixed, as well as a shape pattern based on the intensity of brightness. It can also be recognized as This has been confirmed to show a high correlation and reproducibility even in experimental results comparing color patterns and brightness patterns, and the present invention performs identification based on this principle.

The method of the present invention will be explained below based on the identification device shown in FIGS. 1 and 2.

The identification device indicated by reference numeral l in FIG. 1 includes an imaging section 2. This *R section 2 is configured as shown in FIG. 2, and for example, C0
A D (charge-coupled device) camera 3, a camera stand 4 that supports the camera 3 in a height-adjustable manner, lighting devices 5 and 6 arranged on the left and right sides, and a dark box 8 that covers all of these and eliminates the influence of outside light.
Equipped with etc.

The accuracy increases as the number of pixels of the camera 3 increases, but in this embodiment, a black and white camera with a pixel count of 256 bits was used. Therefore, if the dried vegetables V are stored in the tray 7 so that the tray surface is hidden and placed below the camera 3, the camera 3 can image the dried vegetables V from a predetermined distance.

On the other hand, the video output signal of the camera 3 has a magnitude corresponding to the brightness. This video output signal is then supplied to the binarization circuit 12 and binarized using the level (threshold) S set in the level setting circuit 11. In other words, a value less than level S is converted to "0", and a value equal to or higher than level S is converted to "1".

An image binarized in this way is shown in FIG. The figure is a binary image of dried cabbage, with black parts being "0" and white parts being "1". Further, the output of the binarization circuit 12 is supplied to a window setting circuit 13, and only pixels in a certain section are extracted. In FIG. 3, the area inside the dotted line is a window W indicating a fixed area.

Then, the pixel number calculation circuit 14 counts the number of pixels in one side of the window W, for example, the number of "0" pixels,
The sum 3t is outputted from the output circuit I5. Output circuit 15
The output can be used for display, storage, recording, control, etc. by inputting it into, for example, a computer system.

When images of various dried vegetables of different colors were taken using the identification device I, the results shown in the following table were obtained.

In this case, the number of pixels of any dried cabbage A is 20.
The level S was set to be 0.

In this way, samples of various types of dried vegetables appear as clearly distinguishable differences in the number of pixels, and it is possible to clearly identify the types of dried vegetables that are difficult to identify accurately with the naked eye by comparing the number of pixels. was completed. Note that in this case, an arbitrary sample among the plurality of samples is set as a reference, but other absolute standards may be prepared and set in advance.

On the other hand, as is clear from Figure 4, yellow cabbage (Nl
) and green cabbage (NA), as well as the number of pixels when both were mixed at a ratio of 1:1, and when these were plotted on a graph, a high correlation (98%) was observed. . Thereby, if the desired number of pixels is known in advance, the mixture ratio can be known, and by detecting the number of pixels, it is also possible to know how much other components are mixed.

Although the embodiments have been described in detail above, the present invention is not limited to these embodiments.

For example, although dried vegetables are taken as an example, it can be applied to any food, including seafood, etc., in general, either a single type or a mixture of multiple types. Also, COD is used as a means to obtain pixels.
Although a camera is shown as an example, an image pickup tube type camera may be used.

Furthermore, although binarization is taken as an example, it may be encoded into multiple gradations depending on the signal level. Other detailed composition, shape,
Any changes can be made in the method etc. without departing from the gist of the present invention.

〔Effect of the invention〕

As described above, the food identification method according to the present invention images a food of a single type or a mixture of multiple types, digitizes the brightness of pixels obtained from a certain area, for example, binarizes it according to a preset level, and - Since the food is identified by the number of pixels of the power value, the following effects are obtained.

■ Foods can be identified objectively and accurately because color is quantified.

(2) Since no particular precision is required for the imaging unit and circuit system, the configuration is simple and can be implemented at low cost.

■ In addition to identification, it can be applied to preparation, analysis, etc., and has excellent expandability and versatility.

[Brief explanation of drawings]

Figure 1: Block system diagram of an identification device capable of implementing the method of the present invention, Figure 2: External perspective view of an imaging unit in the identification device, Figure 3: Pattern showing an example of a binarized image in the identification device. Figure 4: Relationship between the number of pixels and the mixing ratio of two different types of dried vegetables. In the drawing, ■ = Identification device 3: CCD camera 11 2-level setting circuit 12: Binarization circuit 13: Window setting circuit V: Dried vegetables S 2-level

Claims (1)

[Scope of Claims] [1] Imaging a single type of food or a mixture of multiple types of food, quantifying the brightness of pixels obtained from a certain area, and identifying the type of food based on this numerical value. A food identification method characterized by: [2] The food identification method according to claim 1, wherein the brightness of pixels is binarized according to a preset level, and identification is performed based on the number of pixels of one value. [3] The food identification method according to claim 1, wherein the food is a dried vegetable.