JPH04292713A - Heating cooker - Google Patents

Heating cooker

Info

Publication number
JPH04292713A
JPH04292713A JP3057183A JP5718391A JPH04292713A JP H04292713 A JPH04292713 A JP H04292713A JP 3057183 A JP3057183 A JP 3057183A JP 5718391 A JP5718391 A JP 5718391A JP H04292713 A JPH04292713 A JP H04292713A
Authority
JP
Japan
Prior art keywords
information
discriminating
neural network
container
signal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP3057183A
Other languages
Japanese (ja)
Inventor
Shigeki Yoshida
茂樹 吉田
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sanyo Electric Co Ltd
Original Assignee
Sanyo Electric Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sanyo Electric Co Ltd filed Critical Sanyo Electric Co Ltd
Priority to JP3057183A priority Critical patent/JPH04292713A/en
Publication of JPH04292713A publication Critical patent/JPH04292713A/en
Pending legal-status Critical Current

Links

Landscapes

  • Control Of High-Frequency Heating Circuits (AREA)
  • Electric Ovens (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

PURPOSE:To form a neural network for discriminating an object by effecting learning based on information on the shadow pattern of an object through irradiation with light and a teaching signal for an object discriminating content, output a discriminating signal and improve cooking basing on the neural work. CONSTITUTION:The shadow of a container 4 is projected to a photo sensor unit 5 by an indoor lamp 2, information on the shadow pattern of the container 4 is detected by the photo sensor unit 5, and the information is inputted to a memory 6. At a timing at which a turn table 3 makes one full turn, the memory 6 outputs the memory information to a neurounit 7 by a timing signal from a timer 13. In which case, the neural network of the neurounit 7 learns based on learning data, and outputs a discriminating result wherein the container 4 is a cup and a liquor bottle. Based on the discriminating result, an optimum cooking course is set by a control part 8 of a sequence, and based on the cooking course, a drive signal is inputted to drive circuits 15 and 16 to execute cooking.

Description

【発明の詳細な説明】[Detailed description of the invention]

【0001】0001

【産業上の利用分野】この発明は、電子レンジ等の加熱
調理器における、容器や食品の形状、大きさ、個数等の
情報判別に関する。
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to determining information such as the shape, size, number, etc. of containers and foods in a cooking device such as a microwave oven.

【0002】0002

【従業の技術】従来から容器や食品の形状、大きさ、個
数等をCCDカメラ等を使って判別し、その判別情報を
調理シーケンスに利用して優れた調理を実現しようとす
ることが行われている。
[Employee technology] Traditionally, the shape, size, number, etc. of containers and foods have been determined using a CCD camera, etc., and the determination information is used in the cooking sequence to achieve excellent cooking. ing.

【0003】0003

【発明が解決しようとする課題】しかしながら、このよ
うな従来の方法によれば、情報判別システムの規模が大
きくなり過ぎたり、高価になるために、実用化されてい
ないのが現状である。また、画像処理も困難であるとと
もに、画像解析に多くの手間がかかる問題点があった。
[Problems to be Solved by the Invention] However, according to such conventional methods, the scale of the information discrimination system becomes too large and the cost becomes too high, so that it has not been put into practical use at present. In addition, image processing is difficult and image analysis requires a lot of effort.

【0004】この発明は上記の事情に鑑みて行ったもの
で、容器や食品の形状、大きさ、個数等の情報判別が簡
単な構成において容易に短時間で行え、判別した情報に
基づいて調理が良好になされる加熱調理器を提供するこ
とを目的とする。
[0004] This invention was developed in view of the above-mentioned circumstances, and it is possible to easily and quickly determine information such as the shape, size, and number of containers and foods with a simple configuration, and to prepare food based on the determined information. It is an object of the present invention to provide a heating cooker that can be used satisfactorily.

【0005】[0005]

【課題を解決するための手段】この発明では、加熱調理
器を、対象物に光を照射する光源と、前記光の照射によ
る対象物の陰パターンを検出する検出部と、前記検出部
からの陰パターン情報と対象物判別内容の教師信号とに
基づいて学習を行って対象物判別のためのニューラルネ
ットワークを予め形成し、前記検出部から情報が入力さ
れると前記ニューラルネットワークにより対象物判別出
力を行うニューロユニットとを備えてなる構成とした。
[Means for Solving the Problems] According to the present invention, a heating cooker includes a light source that irradiates light onto an object, a detection section that detects a shadow pattern of the object due to the irradiation of the light, and a detection section that detects a shadow pattern of the object due to the irradiation of the light. A neural network for object discrimination is formed in advance by learning based on the shadow pattern information and a teacher signal of object discrimination content, and when information is input from the detection section, the neural network outputs object discrimination. The structure includes a neuro unit that performs the following functions.

【0006】[0006]

【作用】この発明によれば、光の照射による対象物の陰
パターンの情報と対象物判別内容の教師信号とに基づい
て学習を行って対象物判別のためのニューラルネットワ
ークを形成し、次に、検出部から陰パターン情報が入力
されるとニューラルネットワークにより対象物判別出力
を行う。
[Operation] According to the present invention, a neural network for object discrimination is formed by learning based on the information on the shadow pattern of the object due to light irradiation and the teacher signal of the object discrimination content, and then When the shadow pattern information is input from the detection unit, the neural network performs object discrimination and outputs.

【0007】[0007]

【実施例】図1は、この発明の加熱調理器としての電子
レンジのブロック構成図であり、1は加熱室であって、
加熱室1の一方の側壁に光源としての室内灯2が取りつ
けられている。3はターンテーブルであり、ターンテー
ブル3上には容器4が載置されている。5は他方の側壁
に設けられる陰パターン検出部としての光センサユニッ
トで、光センサユニット5は、図2に示すような受光素
子5aがマトリックス状に配置された受光面5bを備え
、その受光面5bが室内灯2およびターンテーブル3側
に向くように設けられている。また、加熱室1内の上部
にはマグネットロン10が、下部にはヒータ11がそれ
ぞれ設けられている。
DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 is a block diagram of a microwave oven as a heating cooker of the present invention, and 1 is a heating chamber,
An indoor light 2 as a light source is attached to one side wall of the heating chamber 1. 3 is a turntable, and a container 4 is placed on the turntable 3. Reference numeral 5 designates an optical sensor unit as a negative pattern detection section provided on the other side wall, and the optical sensor unit 5 includes a light receiving surface 5b on which light receiving elements 5a are arranged in a matrix as shown in FIG. 5b is provided so as to face the indoor light 2 and turntable 3 side. Further, a magnetron 10 is provided in the upper part of the heating chamber 1, and a heater 11 is provided in the lower part.

【0008】6は光センサユニット5からの信号を記憶
するメモリ、13はメモリ6にタイマ信号を与えるタイ
マ、7はメモリ6からの信号に基づいて対象物判別出力
を行うニューロユニット、8はニューロユニット7から
の出力に対応して、メモリ14から選択されるシーケン
スに基づいてマネットロン10、ヒータ11の駆動回路
15,16それぞれに駆動信号を与えるシーケンス制御
部である。17は操作部である。
6 is a memory that stores the signal from the optical sensor unit 5; 13 is a timer that provides a timer signal to the memory 6; 7 is a neuro unit that outputs object discrimination based on the signal from the memory 6; and 8 is a neuron. This is a sequence control section that applies drive signals to the drive circuits 15 and 16 of the manetron 10 and the heater 11, respectively, based on the sequence selected from the memory 14 in response to the output from the unit 7. 17 is an operation section.

【0009】上記ニューロユニット7は、陰パターン情
報と対象物判別内容の教師信号とに基づいて学習を行っ
て対象物判別のためのニューラルネットワークを形成し
、さらに、対象物に関する入力値があるとそのニューラ
ルネットワークにより対象物判別出力を行うように構成
されている。
[0009] The neuro unit 7 forms a neural network for object discrimination by performing learning based on the shadow pattern information and the teacher signal of the object discrimination content, and furthermore, when there is an input value regarding the object, The neural network is configured to output object discrimination.

【0010】以下、上記電子レンジにおける判別動作に
ついて説明する。
[0010] The discrimination operation in the above microwave oven will be explained below.

【0011】まず、室内灯2の点灯により、容器4の陰
が光センサユニット5に投影され、これにより、光セン
サユニット5で容器4の陰パターン情報が検出され、メ
モリ6に与えられる。メモリ6では、ターンテーブル3
が一回転したタイミングでタイマ13から与えられるタ
イミング信号によってその記憶情報をニューロユニット
7に与える。
First, when the indoor light 2 is turned on, the shadow of the container 4 is projected onto the photosensor unit 5, whereby the photosensor unit 5 detects the shade pattern information of the container 4 and provides it to the memory 6. In memory 6, turntable 3
The stored information is given to the neuro unit 7 by a timing signal given from the timer 13 at the timing of one revolution.

【0012】ニューロユニット7のニューラルネットワ
ークは、入力層、中間層、出力層の3層からなり、学習
アルゴリズムはバックプロパゲーションである。このニ
ューラルネットワークの入力層に陰パターン情報が入力
されると、ニューラルネットワークは学習データに沿っ
て学習して出力層から容器4が、カップ、徳利、スープ
皿等であるとの判別結果を出力する。
The neural network of the neuro unit 7 consists of three layers: an input layer, an intermediate layer, and an output layer, and the learning algorithm is backpropagation. When the negative pattern information is input to the input layer of this neural network, the neural network learns according to the learning data and outputs the determination result that the container 4 is a cup, sake bottle, soup plate, etc. from the output layer. .

【0013】このようにして得られた判別結果に基づい
てシーケンス制御部8で最適な調理コースを設定し、か
つ、その調理コースに基づいて駆動信号が駆動回路14
,15に与えられることにより調理が実行される。
Based on the determination result obtained in this manner, the sequence control unit 8 sets an optimal cooking course, and the drive signal is transmitted to the drive circuit 14 based on the cooking course.
, 15, the cooking is performed.

【0014】上記の判別方法によれば、学習によりニュ
ーラルネットワークが自己形成されるので、従来におけ
るような容器毎の画像解析の手間が省け、また解析作業
のミスも問題もなくなり、作業の簡素化が図れる。また
、ニューラルネットワークの特徴上並列処理によって全
ての入力から該当容器を連想して判別するので、判別率
が高く、センサ感度にムラがあっても判別能力が従来の
ようには低下することがない。ニューラルネットワーク
は対象があいまいさを持つ場合に有効に機能するので、
例えば、判別時における容器の設置位置が少しぐらい学
習時の設置位置とずれていても判別が支障無く行われ、
この点においても、作業の簡素化、判別率の向上が可能
となる。くわえて、CCDカメラを用いる判別システム
に比して、小規模に、低コストで形成できる。
[0014] According to the above discrimination method, a neural network is self-formed through learning, so the trouble of image analysis for each container as required in the past can be saved, and there are no errors or problems in the analysis work, which simplifies the work. can be achieved. In addition, due to the characteristics of the neural network, since it uses parallel processing to associate all inputs with the corresponding container and discriminate, the discrimination rate is high, and even if sensor sensitivity is uneven, the discrimination ability does not deteriorate like in the past. . Neural networks work effectively when the target has ambiguity, so
For example, even if the installation position of the container at the time of discrimination is slightly different from the installation position at the time of learning, the discrimination will be performed without any problem.
In this respect as well, it is possible to simplify the work and improve the discrimination rate. In addition, it can be formed on a smaller scale and at lower cost than a discrimination system using a CCD camera.

【0015】なお、上記の実施例では容器の形状を判別
する構成としたが、食品の形状、大きさ、個数等を判別
することもできる。さらに、光源の数や配置パターンを
替えることにより、種々異なる判別結果が得ることがで
きる。
In the above embodiment, the shape of the container is determined, but it is also possible to determine the shape, size, number, etc. of the food. Furthermore, by changing the number of light sources and the arrangement pattern, various different discrimination results can be obtained.

【0016】[0016]

【発明の効果】この発明は上記のような構成により、容
器や食品の形状、大きさ、個数等の情報判別が簡単な構
成において容易に短時間で行え、とくに、ニューラルネ
ットワークの使用により高い判別結果が得られるので、
これにより、その判別結果を使用して調理が良好になさ
れる加熱調理器を提供できる。
[Effects of the Invention] With the above-described configuration, the present invention can easily and quickly determine information such as the shape, size, and number of containers and foods. Because you can get results,
Thereby, it is possible to provide a heating cooker that can cook food well using the determination result.

【図面の簡単な説明】[Brief explanation of the drawing]

【図1】この発明の電子レンジのブロック構成図。FIG. 1 is a block diagram of a microwave oven according to the present invention.

【図2】光センサユニットの受光面の正面図。FIG. 2 is a front view of the light-receiving surface of the optical sensor unit.

【符号の説明】[Explanation of symbols]

2    室内灯(光源) 5    光センサユニット(検出部)7    ニュ
ーロユニット
2 Indoor light (light source) 5 Optical sensor unit (detection section) 7 Neuro unit

Claims (1)

【特許請求の範囲】[Claims] 【請求項1】  対象物に光を照射する光源と、前記光
の照射による対象物の陰パターンを検出する検出部と、
前記検出部からの陰パターン情報と対象物判別内容の教
師信号とに基づいて学習を行って対象物判別のためのニ
ューラルネットワークを予め形成し、前記検出部から情
報が入力されると前記ニューラルネットワークにより対
象物判別出力を行うニューロユニットと、を備えてなる
加熱調理器。
1. A light source that irradiates a target object with light; a detection unit that detects a shadow pattern of the target object due to the irradiation of the light;
A neural network for object discrimination is formed in advance by performing learning based on the shadow pattern information from the detection section and a teacher signal of object discrimination content, and when information is input from the detection section, the neural network A heating cooker comprising: a neuro unit that outputs an object discrimination output based on the information provided by the neuron unit;
JP3057183A 1991-03-20 1991-03-20 Heating cooker Pending JPH04292713A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP3057183A JPH04292713A (en) 1991-03-20 1991-03-20 Heating cooker

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP3057183A JPH04292713A (en) 1991-03-20 1991-03-20 Heating cooker

Publications (1)

Publication Number Publication Date
JPH04292713A true JPH04292713A (en) 1992-10-16

Family

ID=13048392

Family Applications (1)

Application Number Title Priority Date Filing Date
JP3057183A Pending JPH04292713A (en) 1991-03-20 1991-03-20 Heating cooker

Country Status (1)

Country Link
JP (1) JPH04292713A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05312329A (en) * 1992-03-09 1993-11-22 Matsushita Electric Ind Co Ltd Cooker

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05312329A (en) * 1992-03-09 1993-11-22 Matsushita Electric Ind Co Ltd Cooker

Similar Documents

Publication Publication Date Title
RU2536751C2 (en) Automatic adjustment of lighting
TW586076B (en) Image input apparatus, subject identification system, subject verification system and image input method
MX2010012262A (en) Interactive input system with controlled lighting.
CN110235906A (en) It is heat-treated monitoring system
CA2138272A1 (en) A technique to count objects in a scanned image
JPS57161708A (en) Focusing detector having variable visual field of detection
JPS5957108A (en) System for judging damage of paper
JPH04292713A (en) Heating cooker
WO2018173987A1 (en) Heating cooking device
WO2002090876A2 (en) Method and apparatus for determining the coordinates of an object
CN114816114A (en) Photosensitive touch interaction method
JPH035622A (en) Cooking control device
JPH04118546A (en) Bottle inspection device
JP2902801B2 (en) Cooker
JPH02145904A (en) Pattern inspection and pattern inspecting device used therefor
CN108981588B (en) Cup opening height measuring device and measuring method
CN109357616B (en) Automatic frequency conversion light wave stove
JPH0514260B2 (en)
JPS63247680A (en) Image tracking device
JP2003254911A (en) Rice grain grade determination method and its device
JP3088506B2 (en) kitchenware
JPH0439602U (en)
JPWO2019198621A1 (en) Cooker
JPS6214794B2 (en)
JPS577505A (en) Detecting method for excess and deficient turn-tightening of cap and device thereof